# Index Agentica > An agent-first directory of skills, harnesses, MCP servers, tools, protocols and APIs: built by agents, for agents. 654 entries across 11 categories. Static, no auth, crawl freely. Contribute via pull request to https://github.com/Drudley/indexagentica. ## Start here (agents) - [MCP server](https://mcp.indexagentica.com/mcp): remote MCP (Streamable HTTP, no auth, read-only). Tools: search, get_entry, get_content, list_categories, request_listing (ask for something missing to be added) - [Request a listing](https://mcp.indexagentica.com/v1/requests): POST JSON {wanted, category, url?, reason?, requester?} to https://mcp.indexagentica.com/v1/requests (or MCP tool request_listing); GET it for the most-requested list (also https://indexagentica.com/requested/ and https://indexagentica.com/api/requests.json). Merged by similarity into vote counts; nothing is listed until the Curator verifies it. Limits: 5/hour, 20/day per client - [REST search API](https://mcp.indexagentica.com/search?q=mcp): base https://mcp.indexagentica.com; GET /search?q=, /entries/{id}, /categories, /content; OpenAPI at https://mcp.indexagentica.com/openapi.json - [Usage stats](https://mcp.indexagentica.com/stats): live JSON usage counts (page views, outbound clicks, skill downloads by skill, MCP tool calls per tool, top MCP clients, API requests, agent/human split; our own traffic excluded) for 24h, 7 days and all time; what is counted: https://indexagentica.com/agents/#privacy - [JSON index](https://indexagentica.com/api/index.json): everything at once, as JSON - [llms-full.txt](https://indexagentica.com/llms-full.txt): everything at once, as markdown - [One entry](https://indexagentica.com/entries/{id}.md): markdown; JSON at https://indexagentica.com/api/entries/{id}.json - [Long-form index](https://indexagentica.com/api/longform.json): guides, comparisons, stacks and skills - [Contribute](https://indexagentica.com/contribute.json): how to add an entry Each entry is available as HTML (https://indexagentica.com/entries/{id}/), markdown (https://indexagentica.com/entries/{id}.md) and JSON (https://indexagentica.com/api/entries/{id}.json). ## Machine-readable - [llms-full.txt](https://indexagentica.com/llms-full.txt): every entry in full markdown - [JSON index](https://indexagentica.com/api/index.json): all entries with metadata and counts - [OpenAPI](https://indexagentica.com/openapi.json): OpenAPI 3.1 description of the JSON endpoints - [Entry schema](https://indexagentica.com/schema/entry.schema.json): JSON Schema (draft 2020-12) for one entry - [Long-form index](https://indexagentica.com/api/longform.json): guides, comparisons, stacks and skills with metadata (per item: https://indexagentica.com/api/longform/{route}/{id}.json) - [For agents](https://indexagentica.com/agents/): how to consume and contribute ## Contribute - [contribute.json](https://indexagentica.com/contribute.json): machine-readable contribution guide: rules, entry template, PR steps, issue body template - [Pull request path](https://indexagentica.com/agents/#contribute-pr): add content/{category}/{id}.json to https://github.com/Drudley/indexagentica, run node scripts/validate.mjs, open a PR - [Issue path](https://indexagentica.com/agents/#contribute-issue): open a structured "New entry" issue (form: https://github.com/Drudley/indexagentica/issues/new?template=new-entry.yml); a maintainer's approved label turns it into a PR - [Entry template](https://github.com/Drudley/indexagentica/blob/main/schema/entry.template.json): copy-paste JSON - [Corrections / removals](https://github.com/Drudley/indexagentica/issues/new?template=correction.yml) - Guides, comparisons, stacks and skills are written by maintainers (no issue form yet) ## Guides Step-by-step guides for building with and for AI agents. HTML: https://indexagentica.com/guides/ JSON: https://indexagentica.com/api/longform/guides.json - [Confine a coding agent's filesystem MCP access](https://indexagentica.com/guides/confine-a-coding-agents-filesystem-mcp.md): Separate the workspace a coding agent sees from the files its MCP server can touch. A practical review of allowed directories, legacy Roots, read-only tools, symlinks and hard links, with a disposable acceptance checklist. - [Give an agent durable memory with SurrealDB Agent Memory](https://indexagentica.com/guides/use-surrealdb-agent-memory.md): Connect an agent to SurrealDB Agent Memory over MCP or the Python/TypeScript SDKs: Context + Bearer key, remember/recall/forget, provenance and supersession, and what the free Sandbox actually needs. - [Let an agent send email safely through the Resend MCP server](https://indexagentica.com/guides/let-an-agent-send-email-safely.md): Give an agent email through Resend's MCP server without letting it mail anyone, anything, at any time: pin the sender, fence off local files, draft first, deny-by-default tool gating, and a human approval step that shows recipients and subject. Tested offline against resend-mcp 2.28.0. - [Make your site and API discoverable by agents](https://indexagentica.com/guides/publish-agent-discovery-files.md): Publish the files agents look for: an RFC 9727 API catalog, an AI Catalog, an MCP Server Card, an Agent Skills index and llms.txt. Minimal valid examples, the headers each spec asks for, each spec's real status, and how to check the result with our discovery probe. - [Publish an MCP server so agents can find it](https://indexagentica.com/guides/publish-an-mcp-server.md): Build a small MCP server with FastMCP, test it with the MCP Inspector CLI, publish its metadata to the official MCP Registry with mcp-publisher, then get it into GitHub's registry, Glama, the Docker MCP Catalog and Index Agentica. - [Screen tool and web output for prompt injection before your agent reads it](https://indexagentica.com/guides/screen-tool-output-for-prompt-injection.md): Put a check between untrusted tool results and the model: Llama Prompt Guard 2 for injection attempts, LlamaFirewall's scanners for hidden text and generated code, and Llama Guard for content safety. Includes a tested screening wrapper and the limits of each layer. - [Drive a headless Godot editor over MCP](https://indexagentica.com/guides/drive-a-headless-godot-editor-over-mcp.md): Run a Godot 4.7 editor with no display on a Linux box or CI runner and let a coding agent edit scenes and scripts through Beckett, Godot Editor MCP or Godot AI. Includes tested commands, a stdlib Python probe, and the security checks we ran. - [Evaluate an AI agent with open-source eval and observability tools](https://indexagentica.com/guides/evaluate-an-ai-agent.md): A hands-on loop for agent quality: instrument with OpenTelemetry, collect traces, turn real traces into a dataset, write code, LLM-as-judge and human evaluators, run offline experiments, then monitor production and gate pull requests in CI. - [Give your coding agent up-to-date library docs over MCP (Context7, GitMCP, DeepWiki, Microsoft Learn)](https://indexagentica.com/guides/give-your-coding-agent-up-to-date-docs.md): Stop your coding agent from guessing at APIs that changed after its training cutoff. Connect free remote docs MCP servers (Context7, GitMCP, DeepWiki, Microsoft Learn) to Claude Code, Codex or Cursor, learn which tool to call for what, and keep a self-hosted fallback for private docs. - [Scan agent-written code for vulnerabilities with the Semgrep MCP server](https://indexagentica.com/guides/scan-agent-written-code-with-semgrep-mcp.md): Give a coding agent a deterministic security scanner. Install the Semgrep CLI, run its built-in MCP server (`semgrep mcp`), wire it into Claude Code, Cursor, VS Code, Codex or Kiro, and call semgrep_scan and custom-rule scans. Includes two gotchas we hit, and when SonarQube's MCP server fits better. - [Self-host a code-execution API for agents with Piston or Judge0](https://indexagentica.com/guides/self-host-a-code-execution-api.md): Run Piston or Judge0 on your own server to give an agent a stateless run_code tool for many languages: what each one isolates, the host requirements that decide between them, the limits to set, and a tested tool wrapper. - [Run agent-generated code safely in a sandbox](https://indexagentica.com/guides/run-untrusted-code-in-a-sandbox.md): A defense-in-depth recipe for executing LLM-written or user-supplied code: pick an isolation boundary, lock down egress, keep secrets out, cap time and resources, and treat the output as untrusted. - [Bridge stdio and remote MCP servers: mcp-remote, Supergateway, mcp-proxy and mcpo](https://indexagentica.com/guides/bridge-stdio-and-remote-mcp-servers.md): Put a local stdio MCP server on HTTP so remote agents can reach it, or plug a remote server into a client that only speaks stdio. Covers mcp-remote, Supergateway, mcp-proxy and mcpo: which direction each one bridges, exact commands, how to lock the endpoint down, and two dependency breakages we hit. - [Use the Index Agentica MCP server: the five real tools, their schemas and the mistakes to avoid](https://indexagentica.com/guides/use-the-indexagentica-mcp-server.md): A reference for the five tools that mcp.indexagentica.com actually exposes (search, get_entry, get_content, list_categories and request_listing), with input schemas, live example calls and responses, the matching REST endpoints, and the wrong tool names and arguments that clients send most often. - [Test a tool-using agent for prompt injection with AgentDojo](https://indexagentica.com/guides/test-an-agent-for-prompt-injection.md): Measure how often injected tool outputs hijack your agent. Run AgentDojo's built-in suites from the CLI, wire your own model or agent loop in as a pipeline, read utility, utility under attack and targeted attack success, then compare defenses. - [Add OAuth authorization to your own MCP server](https://indexagentica.com/guides/add-oauth-to-your-mcp-server.md): A server-side walkthrough of the MCP 2026-07-28 authorization spec: publish RFC 9728 protected resource metadata, answer 401 and 403 challenges, verify JWT audience per RFC 8707, enforce per-tool scopes, and never pass tokens through. Tested with the MCP TypeScript SDK v2. - [Test your MCP server with in-process tests and Inspector CI checks](https://indexagentica.com/guides/test-your-mcp-server.md): Automated tests for a TypeScript MCP server: call tools in-process through the SDK's handler.fetch, assert on structuredContent and isError, snapshot the tool list so schema changes fail review, test the bearer-token gate, spawn the stdio build, and add MCP Inspector CLI checks to CI. - [Convert documents to Markdown for agents with MarkItDown and Docling](https://indexagentica.com/guides/convert-documents-to-markdown-for-agents.md): Turn PDFs, Office files and other documents into Markdown or chunks an agent can read, with Microsoft's MarkItDown for speed and Docling for layout and tables, then expose either one to an agent over MCP. - [Give an agent a Lightning wallet with Nostr Wallet Connect](https://indexagentica.com/guides/lightning-payments-with-nwc.md): How to let an agent pay Lightning invoices and check its balance through Nostr Wallet Connect (NIP-47), using a budget-capped connection from Alby Hub or LNbits, the Alby JS SDK or the Alby MCP server. - [Agent auth and delegated access, step by step](https://indexagentica.com/guides/agent-auth-and-delegated-access.md): How an agent acts for a user without holding their passwords: CIMD client registration, the MCP 2026-07-28 OAuth flow with resource indicators and audience checks, no token passthrough, vaulted third-party tokens, CIBA approvals and Cross App Access (ID-JAG). - [Add MCP servers to Claude Code](https://indexagentica.com/guides/add-mcp-servers-to-claude-code.md): Connect Claude Code to remote and local MCP servers from the command line, choose the right scope, keep tokens out of shared config, and check that each server connected, using GitHub and Playwright as examples. - [Connect an agent to a remote MCP server](https://indexagentica.com/guides/connect-an-agent-to-a-remote-mcp-server.md): How remote MCP works over Streamable HTTP in the 2026-07-28 spec, how OAuth sign-in is discovered, and copy-paste configs for Claude Code, Codex, Cursor, Gemini CLI, VS Code and Claude connectors. - [Give an agent long-term memory](https://indexagentica.com/guides/give-an-agent-long-term-memory.md): How to make an agent remember users, facts and lessons across sessions, choosing between file-based memory, a memory layer such as Mem0, a temporal knowledge graph such as Zep or Graphiti, a stateful agent platform such as Letta, or your own store. - [Pay for an API as an agent with x402](https://indexagentica.com/guides/pay-for-an-api-with-x402.md): How an agent pays per request for an HTTP API or MCP tool with x402 v2, from reading the 402 response to signing a USDC payment with spend caps, on testnet first. ## Comparisons Side-by-side comparisons of directory entries on concrete criteria. HTML: https://indexagentica.com/compare/ JSON: https://indexagentica.com/api/longform/compare.json - [Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth](https://indexagentica.com/compare/fine-tuning-frameworks.md): Compare Axolotl, LLaMA-Factory and Unsloth as SFT, LoRA/QLoRA and preference-tuning frameworks for tool-use models: documented methods, config style, chat/tool datasets, hardware backends, licences and current versions. Cross-links the agent RL stacks comparison. - [Structured-output libraries compared — Outlines, XGrammar, Guidance and llguidance](https://indexagentica.com/compare/structured-output-libraries.md): Compare Outlines, XGrammar, Guidance and llguidance by constraint form (regex, JSON Schema, CFG), documented engine integrations, licences, current PyPI versions and official JSON Schema coverage limits. The libraries compose: Outlines and Guidance can sit on these backends. - [Code-generation evals compared — EvalPlus, BigCodeBench and LiveCodeBench](https://indexagentica.com/compare/code-generation-eval-benchmarks.md): Pick a code-generation evaluation suite by what it stress-tests: expanded unit tests, library-heavy software tasks, or continuously dated contest problems. Agentless is a SWE-bench repair baseline, not a fourth benchmark. - [Agent RL stacks compared — verl, SkyRL, Agent Lightning and ART](https://indexagentica.com/compare/agent-reinforcement-learning-stacks.md): Choose an agent reinforcement-learning stack by the layer you need: distributed training, long-horizon environments, an existing-harness gateway, or a trajectory-and-reward client. Backend ownership matters more than a headline benchmark. - [Memory layers for AI agents](https://indexagentica.com/compare/agent-memory-layers.md): Mem0, LangMem, the Claude memory tool, Graphiti, Zep, Cognee, Letta and SurrealDB Agent Memory compared on memory model, who writes memories, self-hosting and license, hosted pricing, MCP servers, SDK languages and framework ties. - [Newer agent eval sets for data, terminals and multi-agent conflict](https://indexagentica.com/compare/newer-agent-eval-sets.md): AgenticDataBench, TermGrade and CLASHarness compared: what each measures, task counts, how scoring works, how to run them, and licenses. Cross-links the broader agent-benchmarks comparison. - [Observability and eval platforms for AI agents](https://indexagentica.com/compare/agent-observability-platforms.md): Langfuse, LangSmith, Arize Phoenix, Braintrust, Opik and Laminar compared on license, self-hosting, OpenTelemetry ingestion, MCP access to your traces, free tiers, paid entry prices and built-in evaluation. - [Runtime guardrails for agents: Guardrails AI, NeMo Guardrails, Invariant and HOL Guard](https://indexagentica.com/compare/agent-guardrail-frameworks.md): Four open-source guardrail layers compared: where each one sits, what a rule looks like, whether it can check tool calls, which checks need a model, what leaves your machine and how actively each is maintained. All four were installed and run on 2026-11-01. - [Game engine agent tooling compared: Unreal, Unity, Godot, Roblox and Bevy](https://indexagentica.com/compare/game-engine-agent-tooling.md): How a coding agent reaches into Unreal Engine, Unity, Godot, Roblox Studio and Bevy: the official MCP servers and CLIs, the main community servers, what each one runs on, how it is secured, how many tools it exposes and which ones are deprecated or inactive. - [Payment processor MCP servers compared](https://indexagentica.com/compare/payment-processor-mcp-servers.md): The official MCP servers from Stripe, Square, PayPal, Razorpay and Adyen compared on hosting, authentication, what they cover, licence and maturity, so you can wire an agent to the processor you already use. - [Research memory libraries compared: A-MEM vs MemoryOS vs MemOS vs LightRAG](https://indexagentica.com/compare/research-memory-libraries.md): Four open-source memory systems that started as research papers. What each one stores, how many LLM calls a write costs, whether memories survive a restart, and how close each is to something you can run in an agent today. - [Visual agent workflow builders compared: Langflow vs Dify vs n8n](https://indexagentica.com/compare/visual-agent-workflow-builders.md): Three self-hostable visual canvases for building agents and AI workflows, compared on license, self-hosting, MCP support in both directions, code escape hatches, hosted options and what each is best at. Includes a note on Flowise, whose repo is archived. - [Agent environment frameworks compared: Harbor vs AgentEnv Framework vs Seahaven](https://indexagentica.com/compare/agent-environment-frameworks.md): Three open-source Python frameworks for building the environments agent evals and RL runs happen in: Harbor (container tasks), Scale AI's AgentEnv Framework and Kiln AI's Seahaven (synthetic SQLite worlds). Covers tasks, grading, compute, agent interface, interop and license. - [Memory servers for coding agents compared: m3 Memory vs agentmemory vs Basic Memory vs MCP Memory Service](https://indexagentica.com/compare/coding-agent-memory-servers.md): Four self-hosted memory servers that give Claude Code, Codex, Cursor and other MCP clients one shared memory across sessions and tools. Covers install, storage, search, how memories get captured, hosted options and license. - [MCP server frameworks compared: FastMCP vs mcp-use vs the official Python and TypeScript SDKs](https://indexagentica.com/compare/mcp-server-frameworks.md): Four ways to build an MCP server in 2026: the official Python SDK (v2) and TypeScript SDK (v2), Prefect's FastMCP and Manufact's mcp-use. Covers languages, schemas, transports, auth, MCP Apps (UI), local testing, deployment and license. - [Work-management MCP servers compared: Asana vs monday.com vs Linear vs Notion vs Atlassian](https://indexagentica.com/compare/work-management-mcp-servers.md): The official hosted MCP servers for five work-management tools (Asana, monday.com, Linear, Notion and Atlassian's Jira/Confluence server), compared on endpoint, auth, read-only options, tool exposure, admin controls and what you can self-host. - [LLM gateways compared: OpenRouter vs Vercel AI Gateway vs Cloudflare AI Gateway vs Portkey vs LiteLLM](https://indexagentica.com/compare/llm-gateways.md): Five ways to put one endpoint between your agents and many model providers: two hosted model marketplaces (OpenRouter, Vercel AI Gateway), Cloudflare's proxy, and two open-source gateways you can self-host (Portkey, LiteLLM). Covers API, fallback, caching, spend controls, MCP, pricing and license. - [LiveKit Agents vs Pipecat vs OpenAI Realtime vs ElevenAgents vs Vapi: building voice agents](https://indexagentica.com/compare/voice-agent-platforms.md): Five ways to give an agent a voice compared: two open-source realtime frameworks (LiveKit Agents, Pipecat), a speech-to-speech model API (OpenAI Realtime) and two hosted voice-agent platforms (ElevenAgents, Vapi). Covers architecture, hosting, telephony, MCP tools, testing, pricing and license. - [OpenClaw vs Hermes Agent vs Pi: open-source agents you run yourself](https://indexagentica.com/compare/personal-agent-runtimes.md): Three fast-moving open-source agent runtimes compared: OpenClaw (gateway-first personal assistant), Hermes Agent (self-improving agent with memory, skills and cron) and Pi (minimal, extensible coding harness). Covers interfaces, models, memory, skills, MCP, automation, safety defaults and license. - [MCP gateways compared](https://indexagentica.com/compare/mcp-gateways.md): Docker MCP Gateway, Stacklok ToolHive and Arcade MCP Gateways compared on where they run, how they isolate MCP servers, how clients authenticate, tool filtering and context control, policy, audit and rate limits, and licensing. - [Open-source red-teaming tools for LLM apps and agents](https://indexagentica.com/compare/llm-red-teaming-tools.md): Promptfoo, DeepTeam and Giskard compared as red-teaming tools for LLM apps and agents. Covers interface, what they attack, agent and MCP coverage, multi-turn attacks, framework mappings, CI use, and where attack generation and telemetry go. - [DevOps and observability MCP servers compared](https://indexagentica.com/compare/devops-mcp-servers.md): Eight official MCP servers for infrastructure and operations work (Kubernetes, Terraform, Buildkite, Azure DevOps, Heroku, Datadog, Grafana and Sentry) compared on what they cover, where they run, how they authenticate and how far their read-only modes actually go. - [Self-hosted sandboxes for agents compared](https://indexagentica.com/compare/self-hosted-agent-sandboxes.md): Six ways to isolate agent-run code on hardware you control (OpenSandbox, AIO Sandbox, microsandbox, Kubernetes Agent Sandbox, Anthropic's sandbox-runtime and Docker Sandboxes' local mode) compared on isolation, where they run, agent interface, network and secret controls, maturity and license. - [Agent benchmarks compared](https://indexagentica.com/compare/agent-benchmarks.md): Ten widely cited agent benchmarks (SWE-bench, Terminal-Bench, tau-bench, BFCL, MCPMark, GAIA, BrowseComp, WebArena, Mind2Web and OSWorld) compared on what they measure, how many tasks they have, where the agent runs, how runs are scored, where results are published and how they are licensed. - [Database MCP servers compared](https://indexagentica.com/compare/database-mcp-servers.md): Google's MCP Toolbox for Databases and the MongoDB, Neon and Supabase MCP servers compared on what they connect to, where they run, how they authenticate, how read-only mode and scoping work, and what guards their write tools. - [Vector databases for agents compared](https://indexagentica.com/compare/vector-databases-for-agents.md): Chroma, Pinecone, Qdrant, Weaviate, Milvus, LanceDB, turbopuffer and pgvector compared on how they deploy, license, keyword and hybrid search, filtering and tenant isolation, MCP servers and managed pricing. - [IDE and cloud coding agents compared](https://indexagentica.com/compare/ide-and-cloud-coding-agents.md): Cursor, VS Code agent mode, Google Antigravity, Devin and Kiro compared on local versus cloud execution, background tasks, pull-request workflow, model choice, MCP and skills, pricing, and enterprise and privacy controls. - [Agent skill packs, skills CLIs and registries](https://indexagentica.com/compare/agent-skill-packs-and-installers.md): How Agent Skills are installed, discovered and shared across Claude Code, Codex, Gemini CLI, Cursor and Copilot, and how the main installers (skills CLI, plugin marketplaces) and skill packs compare on format, harness support, licence and install command. - [Agent identity and MCP authorization platforms](https://indexagentica.com/compare/agent-identity-and-mcp-auth.md): Descope, Stytch Connected Apps, Auth0 for AI Agents, WorkOS AuthKit and Arcade compared on their role in MCP OAuth, DCR and CIMD support, delegated tokens for third-party APIs, human approval, pricing and SDKs. - [Cloud browsers for AI agents](https://indexagentica.com/compare/cloud-browsers-for-agents.md): Browserbase, Steel, Browserless, Hyperbrowser, Kernel and Anchor Browser compared on how agents connect, MCP servers, pricing, free allowances, login persistence, recordings, self-hosting and whether an agent can get access without a human signing up. - [Agent payment protocols compared](https://indexagentica.com/compare/agent-payment-rails.md): x402, MPP, L402, ACP, AP2 and UCP compared on what each standardizes, payment rails, wire format, governance, spec status and SDKs, so you can tell machine-payment protocols from agent-checkout protocols. - [Code sandboxes for AI agents](https://indexagentica.com/compare/code-sandboxes.md): E2B, Daytona, Modal, Vercel Sandbox, Cloudflare Sandboxes, Fly.io Sprites and microsandbox compared on isolation, pricing, free tier, lifetime, persistence, egress controls, SDKs, GPUs and self-hosting. - [Terminal coding agents compared](https://indexagentica.com/compare/coding-agent-harnesses.md): Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, Cline, goose and Aider compared on license, model access, instruction files, sandboxing, headless mode, MCP and Agent Skills support. - [Web search APIs for agents](https://indexagentica.com/compare/web-search-apis.md): Tavily, Exa, Brave Search, Parallel and Perplexity compared on endpoints, index, list price per 1,000 searches, free allowance and MCP support, for agents that need fresh web results. ## Stacks Curated combinations of tools for a specific agent use case. HTML: https://indexagentica.com/stacks/ JSON: https://indexagentica.com/api/longform/stacks.json - [Post-training a tool-use model — TRL, PEFT, and scale-out RL](https://indexagentica.com/stacks/post-training-tool-use-model.md): A recommended post-training stack for chat and tool-use models: TRL and PEFT for SFT, LoRA/QLoRA, DPO and GRPO, with OpenRLHF and AReaL as the distributed and asynchronous RL options. Cross-links the fine-tuning frameworks and agent RL stacks comparisons. - [Bookkeeping agent stack](https://indexagentica.com/stacks/bookkeeping-agent.md): An agent that reconciles Stripe or Paddle revenue against the books in Xero, reads receipts and statements, and prepares draft entries for an accountant. It runs on read-only credentials, and every write needs a human. - [Data analysis agent stack](https://indexagentica.com/stacks/data-analysis-agent.md): An agent that answers questions from your data: it queries DuckDB files, a ClickHouse warehouse or Postgres through read-only MCP servers, runs heavier analysis in a sandbox, reads spreadsheets and PDFs, and is tested and traced so you can trust the numbers. - [Agent that can buy things](https://indexagentica.com/stacks/agent-that-can-buy-things.md): The pieces for an agent that pays for APIs per call with x402 stablecoins and buys from merchants with controlled virtual cards, with spend limits, proof of user intent and a full audit trail. - [Coding agent starter stack](https://indexagentica.com/stacks/coding-agent-starter.md): A terminal coding agent plus current library docs, GitHub access, a real browser and a sandbox, connected over MCP, with the configuration choices that keep it safe. - [Research agent stack](https://indexagentica.com/stacks/research-agent.md): An agent that searches the web and the scholarly record, reads full sources, runs analysis code in a sandbox and cites what it found, with tracing so you can audit how it got there. ## Downloadable skills (Agent Skills) Downloadable Agent Skills (SKILL.md folders), served raw and as zip archives. HTML: https://indexagentica.com/skills/ JSON: https://indexagentica.com/api/longform/skills.json - [Discover a site's agent interfaces](https://indexagentica.com/skills/discover-agent-interfaces.md): A probe-then-pick workflow for finding the best machine interface a website offers (MCP, A2A, OpenAPI, Agent Skills, llms.txt, NLWeb or WebMCP), with a read-only Python script tested against live sites on 2026-11-01. (zip: https://mcp.indexagentica.com/skills/discover-agent-interfaces.zip) - [Index Agentica lookup](https://indexagentica.com/skills/indexagentica-lookup.md): Query Index Agentica through its live MCP server (exactly five tools: search, get_entry, get_content, list_categories, request_listing), its REST mirror, or the static JSON API and llms.txt, to discover agent tools, MCP servers, APIs and long-form guides, and to propose new entries. (zip: https://mcp.indexagentica.com/skills/indexagentica-lookup.zip) - [Pick an MCP server](https://indexagentica.com/skills/pick-an-mcp-server.md): A repeatable shortlist-compare-probe workflow for selecting an MCP server from Index Agentica, with two scripts that pull candidates from the live REST API and test a remote endpoint's auth without credentials. (zip: https://mcp.indexagentica.com/skills/pick-an-mcp-server.zip) - [Connect a remote MCP server](https://indexagentica.com/skills/connect-remote-mcp.md): Configure, verify and troubleshoot a remote Streamable HTTP MCP server in the major agent clients, including OAuth discovery and protocol-version checks. (zip: https://mcp.indexagentica.com/skills/connect-remote-mcp.zip) - [Pay with x402](https://indexagentica.com/skills/pay-with-x402.md): Read an x402 v2 402 response, check it against a spending policy, pay with an SDK or CLI, and verify the PAYMENT-RESPONSE receipt. (zip: https://mcp.indexagentica.com/skills/pay-with-x402.zip) - [Unreal Engine development for coding agents](https://indexagentica.com/skills/unreal-engine-dev.md): Rules, commands and fixes an AI coding agent needs in an Unreal Engine 5 project, from module layout and reflection macros to headless builds, automation tests, Python editor scripting and Unreal MCP. (zip: https://mcp.indexagentica.com/skills/unreal-engine-dev.zip) ## Skills Reusable agent skills, skill packs and prompt-and-script bundles an agent can load. JSON: https://indexagentica.com/api/skills.json - [AISkills402](https://indexagentica.com/entries/aiskills402.md): x402 store of tested Agent Skills SKILL.md files: pay once in USDC on Base to keep the file, with free re-downloads and free catalog/MCP search. - [Akii: SEO & AI Search Optimizer](https://indexagentica.com/entries/akii-seo-ai-search-optimizer.md): MIT-licensed Claude Code plugin with 12 SEO and AI-search skills, five agents and three commands for audits, content planning, schema and link checks. - [Anthropic Agent Skills (anthropics/skills)](https://indexagentica.com/entries/anthropic-skills.md): Anthropic's public repository of example Agent Skills: folders with a SKILL.md plus scripts and resources that Claude loads dynamically for specialized tasks. - [Caveman](https://indexagentica.com/entries/caveman.md): Viral skill plus proxy for coding agents that cuts tokens by having the agent talk tersely, like a caveman. - [Circle Skills](https://indexagentica.com/entries/circle-skills.md): Circle's open-source Agent Skills for USDC, CCTP bridging, Circle Wallets, Gateway nanopayments and the Arc chain. - [Cloudflare Skills](https://indexagentica.com/entries/cloudflare-skills.md): Cloudflare's official Agent Skills and plugin for building on Workers, the Agents SDK, Durable Objects, Sandbox, Wrangler and the wider Developer Platform; bundles the Cloudflare MCP server. - [Coinbase Agentic Wallet Skills](https://indexagentica.com/entries/coinbase-agentic-wallet-skills.md): Pre-built agent skills for wallet operations (authenticate, fund, send USDC, trade, pay for x402 services) via Coinbase's awal CLI. - [Emil Kowalski's Skills](https://indexagentica.com/entries/emilkowalski-skills.md): Skills for designers and engineers from Emil Kowalski, focused on design engineering. - [Expo Skills](https://indexagentica.com/entries/expo-skills.md): Official Agent Skills from the Expo team for building, deploying, upgrading and debugging Expo / React Native apps and EAS workflows. - [Google Agent Skills](https://indexagentica.com/entries/google-skills.md): Google's official Agent Skills for Google products and Google Cloud, also bundled as plugins (skills + MCP servers) for Claude Code, Codex and Antigravity. - [Google Agents CLI](https://indexagentica.com/entries/google-agents-cli.md): CLI and skills that turn any coding assistant into an expert at creating, evaluating and deploying AI agents on Google Cloud. - [GoVisit Agent Skills Toolkit](https://indexagentica.com/entries/govisit-agent-skills-toolkit.md): MIT toolkit of 22 portable read-only Agent Skills (plus audience plugin bundles) that call GoVisit’s public travel read APIs. - [Hugging Face Skills](https://indexagentica.com/entries/huggingface-skills.md): Agent Skills for AI/ML work on the Hugging Face Hub: dataset creation, model training, evaluation and core hf CLI operations. - [HyperFrames](https://indexagentica.com/entries/hyperframes.md): HeyGen's agent-oriented toolkit and skills for writing HTML and rendering it to video. - [Impeccable](https://indexagentica.com/entries/impeccable.md): Design language skill that makes AI coding harnesses better at front-end design. - [Langfuse Skills](https://indexagentica.com/entries/langfuse-skills.md): Agent Skills that teach coding assistants (Claude Code, Cursor, etc.) to work with Langfuse: traces, prompts, datasets, scores and migration. - [Marketing Skills](https://indexagentica.com/entries/marketingskills.md): Marketing skills for Claude Code and AI agents: CRO, copywriting, SEO, analytics and growth engineering. - [Matt Pocock's Skills](https://indexagentica.com/entries/mattpocock-skills.md): Engineering-focused Agent Skills from Matt Pocock (e.g. tdd, code-review, grill-me), among the most-installed skill packs on skills.sh. - [Microsoft Azure Skills](https://indexagentica.com/entries/azure-skills.md): Official Microsoft agent plugin providing skills and MCP server configurations for Azure scenarios (diagnostics, cost, deployment and more). - [Neon Agent Skills](https://indexagentica.com/entries/neon-agent-skills.md): Agent Skills for Neon serverless Postgres. - [Prisma Skills](https://indexagentica.com/entries/prisma-skills.md): Agent Skills from Prisma for database setup, Prisma Client, the Prisma CLI and Prisma Postgres. - [Remotion Skills](https://indexagentica.com/entries/remotion-skills.md): Agent Skills from the Remotion team for creating videos programmatically with Remotion. - [SandBase Skills](https://indexagentica.com/entries/sandbase-skills.md): Apache-2.0 collection of installable Agent Skills for research, marketing, engineering and business workflows, maintained by SandBase. - [Scientific Agent Skills (K-Dense)](https://indexagentica.com/entries/scientific-agent-skills.md): Library of 177 scientific and research Agent Skills (biology, chemistry, medicine, physics, engineering and more) for agents supporting the Agent Skills standard. - [Sentry for AI (Sentry skills and plugins)](https://indexagentica.com/entries/sentry-for-ai.md): Sentry's official skill library teaching coding agents to set up Sentry SDKs, triage production issues, fix Seer review comments and configure alerts, AI monitoring and OTel. - [skills CLI (npx skills)](https://indexagentica.com/entries/skills-cli.md): Vercel's open agent skills tool: install, update and manage Agent Skills for many coding agents with `npx skills add `. - [Supabase Agent Skills](https://indexagentica.com/entries/supabase-agent-skills.md): Agent Skills that help AI agents build with Supabase, including Postgres best practices. - [Superpowers](https://indexagentica.com/entries/superpowers.md): Agentic skills framework and software-development methodology for coding agents, built from composable skills such as brainstorming, TDD and systematic debugging. - [Trail of Bits Skills](https://indexagentica.com/entries/trailofbits-skills.md): Trail of Bits' plugin marketplace of agent skills for security research, vulnerability detection, testing and audit workflows. - [Unity Agent Plugin](https://indexagentica.com/entries/unity-agent-plugin.md): Unity's official plugin for Claude Code, Codex, Grok Build and Antigravity, bundling Unity's curated game-development skills. - [Unity Skills](https://indexagentica.com/entries/unity-skills.md): Unity's official agent skills for Unity workflows such as monetization, 2D art and Editor installs. Install with `npx skills add Unity-Technologies/skills`. - [Unreal Engine Skills for Claude Code](https://indexagentica.com/entries/unreal-engine-claude-code-skills.md): Epic's Claude Code plugin with an unreal-mcp skill and a SessionStart hook for driving the Unreal Editor through its built-in MCP server. - [Vercel Agent Skills](https://indexagentica.com/entries/vercel-agent-skills.md): Vercel's official collection of Agent Skills, including React best practices, composition patterns and web design guidelines. - [YYLO Skills](https://indexagentica.com/entries/yylo-skills.md): Kanban, task, merge-loop and artifact-workflow skills for coding agents, maintained by the YYLO project. ## Harnesses Agent runtimes, frameworks and harnesses: CLIs, SDKs and orchestration loops. JSON: https://indexagentica.com/api/harnesses.json - [AG2](https://indexagentica.com/entries/ag2.md): Protocol-driven Python framework for cooperating agents, tool-calling loops, human-in-the-loop workflows and multi-agent orchestration. - [Agent S](https://indexagentica.com/entries/agent-s.md): Simular computer-use agent framework that uses screenshots and GUI actions to complete tasks in desktop and browser apps on macOS, Windows and Linux. - [Agenta](https://indexagentica.com/entries/agenta.md): Open-source, self-hostable team workspace for building agents by chat, with tool permissions and approvals, sandboxed sessions, tracing and Slack/WhatsApp/Telegram access. - [AgentScope](https://indexagentica.com/entries/agentscope.md): Python agent framework with ReAct loops, tools and MCP/skills integration, context compaction, memory, permission checks and isolated execution backends. - [Agno](https://indexagentica.com/entries/agno.md): Framework and runtime to build, run and manage agent platforms (Python SDK plus runtime). - [AI SDK (Vercel)](https://indexagentica.com/entries/vercel-ai-sdk.md): Free, open-source TypeScript toolkit from Vercel for building AI apps and agents with streaming, fallbacks and multi-model support. - [Aider](https://indexagentica.com/entries/aider.md): Open-source AI pair programming in your terminal. - [Amp](https://indexagentica.com/entries/amp.md): Coding agent and development environment; run agents unsupervised in cloud orbs or locally with the CLI. - [AppAgent](https://indexagentica.com/entries/appagent.md): Multimodal smartphone agent framework that learns app workflows from exploration or demonstrations and operates through taps and swipes. - [Auggie CLI](https://indexagentica.com/entries/auggie-cli.md): Augment Code's agentic coding CLI for the terminal, backed by its Context Engine, with custom slash commands, MCP, non-interactive mode for CI and GitHub Actions. - [AutoGen](https://indexagentica.com/entries/autogen.md): Microsoft Research's multi-agent programming framework, now in maintenance mode; new projects are pointed to Microsoft Agent Framework. - [CAMEL](https://indexagentica.com/entries/camel.md): Open-source Python multi-agent framework from CAMEL-AI for role-playing agents, data generation, task automation and large-scale world simulation. - [Claude Agent SDK](https://indexagentica.com/entries/claude-agent-sdk.md): Anthropic's SDK for building production agents with Claude Code as a library, in Python and TypeScript. - [Claude Code](https://indexagentica.com/entries/claude-code.md): Anthropic's agentic coding tool that reads your codebase, edits files, runs commands and integrates with dev tools; available in terminal, IDE, desktop and browser. - [Cline](https://indexagentica.com/entries/cline.md): Open-source autonomous coding agent available as an SDK, IDE extension or CLI, with Plan/Act modes and MCP integration. - [Cloudflare Agents SDK](https://indexagentica.com/entries/cloudflare-agents.md): SDK for stateful AI agents on Cloudflare with persistent state, real-time WebSockets, scheduled tasks and remote MCP servers. - [Codex App Server](https://indexagentica.com/entries/codex-app-server.md): Experimental JSON-RPC interface that powers rich Codex clients (e.g. the VS Code extension); embed Codex in your product. Replaces the removed codex mcp-server. - [Continue](https://indexagentica.com/entries/continue.md): Open-source coding agent (CLI, VS Code, JetBrains) whose repo went read-only after a final 2.0.0 release; no longer actively maintained. - [CopilotKit](https://indexagentica.com/entries/copilotkit.md): Open-source SDK for agent-native apps: generative UI, shared state and human-in-the-loop for React, Angular, Vue, React Native, Slack and Teams, built on AG-UI. - [CrewAI](https://indexagentica.com/entries/crewai.md): Python framework for orchestrating role-playing, autonomous AI agents that collaborate as crews and flows. - [Crush](https://indexagentica.com/entries/crush.md): Charm's terminal coding agent: multi-model (OpenAI- or Anthropic-compatible APIs), session-based, LSP-enhanced and extensible with MCP servers. - [Cursor](https://indexagentica.com/entries/cursor.md): AI code editor and coding agent with Agent mode, Rules, Skills, MCP servers and a CLI. - [Deep Agents (LangChain)](https://indexagentica.com/entries/deepagents.md): LangChain's batteries-included agent harness for agents that plan, spawn subagents and use a file system for complex tasks. - [DeepSeek Harness](https://indexagentica.com/entries/deepseek-harness.md): DeepSeek's open-source, plugin-based agent harness (dsh) with a local Web UI, a Python SDK and support for DeepSeek and third-party models. - [Devin CLI](https://indexagentica.com/entries/devin-cli.md): Cognition's local coding agent that runs in your terminal on macOS, Linux, WSL and Windows, with handoff to cloud Devin sessions. - [Devin Desktop (formerly Windsurf)](https://indexagentica.com/entries/devin-desktop.md): Cognition's AI IDE for Mac, Windows and Linux for managing local and cloud agents; windsurf.com now redirects to it. - [Dify](https://indexagentica.com/entries/dify.md): Source-available platform for agentic workflows, RAG pipelines and sandboxed agents on a visual canvas; self-host with Docker or use Dify Cloud. - [DSPy](https://indexagentica.com/entries/dspy.md): Stanford NLP framework for programming, not prompting, language models. - [Factory Droids](https://indexagentica.com/entries/factory-droid.md): Factory's AI coding agents (Droids) that automate coding, testing and deployment. - [fast-agent](https://indexagentica.com/entries/fast-agent.md): CLI-first Python agent harness and framework with end-to-end MCP support (sampling, elicitation, OAuth), Agent Skills, ACP and declarative multi-agent workflows. - [Gemini CLI](https://indexagentica.com/entries/gemini-cli.md): Open-source AI agent from Google that brings Gemini models directly into your terminal. - [GitHub Copilot CLI](https://indexagentica.com/entries/github-copilot-cli.md): Brings GitHub Copilot's coding agent to your terminal to read, write and run code where you work. - [GitHub Copilot cloud agent](https://indexagentica.com/entries/github-copilot-cloud-agent.md): Copilot agent on GitHub.com that takes delegated tasks from issues, pull requests or chat, works in a cloud environment and opens a pull request for review. - [Google Agent Development Kit (ADK)](https://indexagentica.com/entries/google-adk.md): Open-source, code-first toolkit from Google for building, evaluating and deploying multi-agent systems. - [Google Antigravity](https://indexagentica.com/entries/google-antigravity.md): Google's agentic coding platform (app, IDE, CLI, IDE extensions and Python SDK) for orchestrating autonomous subagents, scheduled tasks and code verification. - [goose](https://indexagentica.com/entries/goose.md): Open-source, extensible AI agent (desktop app, CLI and API) that can install, execute, edit and test with any LLM. - [Griptape](https://indexagentica.com/entries/griptape.md): Python framework for agents, sequential pipelines and parallel workflows, with tools, retrieval engines and task memory that keeps large outputs off prompts. - [Haystack](https://indexagentica.com/entries/haystack.md): deepset's open-source orchestration framework for production-ready, context-engineered LLM applications and agents. - [Hermes Agent](https://indexagentica.com/entries/hermes-agent.md): Nous Research's self-improving open-source agent: terminal UI plus messaging gateway, agent-curated memory and skills it writes and refines from experience. - [Inngest AgentKit](https://indexagentica.com/entries/inngest-agentkit.md): TypeScript framework for multi-agent networks with shared typed state, code- or LLM-based routers, MCP tools and durable execution plus tracing on Inngest. - [Jules](https://indexagentica.com/entries/jules.md): Google's autonomous coding agent that plans and runs tasks against your GitHub repos asynchronously, with a REST API and the Jules Tools CLI. - [Kilo Code](https://indexagentica.com/entries/kilo-code.md): Open-source AI coding agent for VS Code, JetBrains, CLI and cloud, with access to 500+ models and bring-your-own-key. - [Kiro](https://indexagentica.com/entries/kiro.md): Agentic engineering environment that turns prompts into executable specs and builds across large codebases with parallel agents. - [LangChain](https://indexagentica.com/entries/langchain.md): Open-source Python and TypeScript framework whose create_agent builds a configurable agent harness from a model, tools, a prompt and middleware. - [Langflow](https://indexagentica.com/entries/langflow.md): Open-source visual builder for AI agents and workflows in Python; every flow can be served as an API or exposed as an MCP server. - [LangGraph](https://indexagentica.com/entries/langgraph.md): Low-level orchestration framework from LangChain for building resilient, stateful agents as graphs. - [LangGraph Swarm](https://indexagentica.com/entries/langgraph-swarm.md): LangChain's Python library for swarm-style multi-agent systems on LangGraph, where agents hand control to each other with handoff tools. - [Langroid](https://indexagentica.com/entries/langroid.md): Python multi-agent framework with task orchestration, typed tool messages, retrieval agents and an MCP-to-tool adapter. - [LiveKit Agents](https://indexagentica.com/entries/livekit-agents.md): Open-source Python (and JS) framework for realtime voice and video agents over WebRTC, with STT/LLM/TTS plugins, telephony, turn detection, MCP tools and tests. - [LlamaIndex](https://indexagentica.com/entries/llamaindex.md): Document-processing platform for AI (open-source LlamaIndex library plus hosted LlamaParse APIs that turn PDFs, scans and Office files into markdown or JSON). - [Mastra](https://indexagentica.com/entries/mastra.md): TypeScript framework for AI agents and apps with memory, tools, MCP and observability built in. - [mcp-agent](https://indexagentica.com/entries/mcp-agent.md): Python framework for composing MCP-connected agents and workflows, with connection lifecycle management and optional Temporal-backed durable execution. - [Microsoft Agent Framework](https://indexagentica.com/entries/microsoft-agent-framework.md): Framework for building, orchestrating and deploying AI agents and multi-agent workflows in Python and .NET; successor to AutoGen. - [mini-swe-agent](https://indexagentica.com/entries/mini-swe-agent.md): Minimal open-source software-engineering agent from the SWE-bench/SWE-agent team: about 100 lines of Python, bash as its only tool, a linear history, any model via LiteLLM. - [n8n](https://indexagentica.com/entries/n8n.md): Fair-code workflow automation platform for AI agents with 1,500+ integrations, an MCP Client node, MCP Server Trigger and a built-in instance-level MCP server. - [OpenAI Agents SDK](https://indexagentica.com/entries/openai-agents-sdk.md): Lightweight framework from OpenAI for multi-agent workflows in Python (with a JS/TS sibling SDK). - [OpenAI Codex CLI](https://indexagentica.com/entries/codex-cli.md): OpenAI's lightweight open-source coding agent that runs in your terminal. - [OpenClaw](https://indexagentica.com/entries/openclaw.md): Open-source personal AI assistant that runs on your own machine behind one Gateway and talks to you over WhatsApp, Telegram, Slack, Discord, iMessage and 20+ other channels. - [OpenCode](https://indexagentica.com/entries/opencode.md): The open-source AI coding agent, built for the terminal. - [OpenHands](https://indexagentica.com/entries/openhands.md): Open-source, model-agnostic platform for cloud coding agents. - [Pi](https://indexagentica.com/entries/pi-coding-agent.md): Minimal, extensible coding-agent harness and TypeScript toolkit (unified LLM API, agent core, TUI) from Earendil; customize with extensions, skills and prompt templates. - [Pipecat](https://indexagentica.com/entries/pipecat.md): Open-source Python framework from Daily for realtime voice and multimodal agents: composable pipelines, 80+ AI service integrations, multi-agent handoffs and client SDKs. - [Pydantic AI](https://indexagentica.com/entries/pydantic-ai.md): Typed Python agent framework from the Pydantic team covering agents, realtime voice, image generation and embeddings across many models. - [Qwen Code](https://indexagentica.com/entries/qwen-code.md): Open-source AI coding agent for the terminal from the Qwen team. - [Roo Code](https://indexagentica.com/entries/roo-code.md): Shut down May 15, 2026: open-source VS Code coding agent (a Cline fork) with Code, Architect, Ask, Debug and custom modes; repo archived. - [SandBase Harness](https://indexagentica.com/entries/sandbase-harness.md): Local-first Apache-2.0 agent runtime with sandboxed sessions, memory, credentials, MCP toolsets, audit/replay and a local Console. - [Semantic Kernel](https://indexagentica.com/entries/semantic-kernel.md): Microsoft's open-source SDK for integrating LLM capabilities quickly and easily into your apps. - [smolagents](https://indexagentica.com/entries/smolagents.md): Hugging Face's barebones Python library for agents that think in code. - [Strands Agents](https://indexagentica.com/entries/strands-agents.md): Open-source, model-driven SDK and ready-made harness for building AI agents in Python and TypeScript, with MCP, multi-agent patterns, memory, guardrails, tracing and evals. - [SWE-agent](https://indexagentica.com/entries/swe-agent.md): Princeton/Stanford research agent that lets an LM fix real GitHub issues, solve CTFs or run custom tasks, configured by one YAML file. - [TapeAgents](https://indexagentica.com/entries/tapeagents.md): Agent framework built around structured replayable session tapes for debugging, resuming, serving and improving single agents or multi-agent teams. - [VS Code Agents (agent mode)](https://indexagentica.com/entries/vscode-agents.md): Agent mode in Visual Studio Code: an agent finds relevant code, edits across files and runs checks in your workspace while you review the changes. - [Warp](https://indexagentica.com/entries/warp.md): Agentic development environment built from the terminal, with a built-in coding agent or your own CLI agent; client source now on GitHub (AGPL-3.0). - [Zed (Zed Agent)](https://indexagentica.com/entries/zed.md): Open-source, high-performance code editor with a native agent (Zed Agent), external ACP agents, terminal agent threads, MCP servers and skills. ## MCP Servers Model Context Protocol servers, local or remote, that give agents tools and data. JSON: https://indexagentica.com/api/mcp-servers.json - [Adyen MCP Server](https://indexagentica.com/entries/adyen-mcp.md): Official alpha MCP server for Adyen Checkout and Management APIs: sessions, payment links, refunds, terminals and webhooks. - [Aident Loadout](https://indexagentica.com/entries/aident-loadout.md): Hosted MCP server and CLI that gives coding and chat agents access to 1,000+ connected apps, with credentials kept in Aident Vault and every action audited. - [AIHOT MCP](https://indexagentica.com/entries/aihot-mcp.md): Remote, read-only MCP server for Chinese-language AI news, keyword searches, story timelines, and dated reports. - [Airbyte MCP](https://indexagentica.com/entries/airbyte-mcp.md): Airbyte's hosted remote MCP server (Streamable HTTP, OAuth) for building and fixing data pipelines and, with the context layer, reading live source and warehouse data. - [Alby MCP Server](https://indexagentica.com/entries/alby-mcp.md): MCP server that connects a Bitcoin Lightning wallet to an LLM via Nostr Wallet Connect, with knowledge of NWC, LNURL and L402. - [Anaconda MCP](https://indexagentica.com/entries/anaconda-mcp.md): Anaconda's hosted, read-only MCP server that gives coding agents conda package facts, curated CVE data with fixed versions, org channel policy and forum search. - [Anansi Haven](https://indexagentica.com/entries/anansi-haven.md): Free-beta remote MCP and A2A home base for agents: no-key utilities, a tools catalog, optional memory, directory and job board, with live Base USDC/$ANANSI checkout. - [Anchor Browser MCP](https://indexagentica.com/entries/anchor-mcp.md): Anchor's hosted MCP servers give agents isolated cloud browsers with stealth, captcha solving, managed logins and saved automations. - [Ankr Agent RPC MCP](https://indexagentica.com/entries/ankr-agent-rpc-mcp.md): Ankr's MCP server of blockchain read tools (decoded transactions, logs, balances, contract metadata, prices), paid per call over x402 in USDC or with an Ankr API key. - [Apify MCP Server](https://indexagentica.com/entries/apify-mcp-server.md): Hosted and open-source MCP server that lets agents run thousands of Apify Store Actors (scrapers, crawlers, automations) for social media, search, maps, e-commerce and any website. - [Asana MCP Server](https://indexagentica.com/entries/asana-mcp.md): Asana's hosted remote MCP server (V2, Streamable HTTP, OAuth) giving AI clients access to tasks, projects and the Asana Work Graph. - [Astrocade MCP](https://indexagentica.com/entries/astrocade-mcp.md): Hosted remote MCP server (OAuth) that lets coding agents build, edit and publish browser games to an Astrocade account and its public game feed. - [Atlassian Rovo MCP Server](https://indexagentica.com/entries/atlassian-rovo-mcp.md): Atlassian's official remote MCP server securely connecting Jira, Confluence, Jira Service Management, Bitbucket and more to AI clients. - [AWS MCP Servers (awslabs)](https://indexagentica.com/entries/aws-mcp-servers.md): Suite of open-source, specialized MCP servers from AWS Labs for working with AWS services. - [Azure DevOps MCP Server](https://indexagentica.com/entries/azure-devops-mcp-server.md): Microsoft's MCP server for Azure DevOps: projects, repos, pull requests, work items, pipelines and builds, wikis, test plans and Advanced Security alerts. - [Basic Memory](https://indexagentica.com/entries/basic-memory.md): Local-first MCP server that gives AI assistants persistent memory stored as Markdown files in a knowledge base you own. - [Beckett (Godot MCP)](https://indexagentica.com/entries/beckett-godot-mcp.md): Zero-sidecar MCP server that runs inside the Godot 4 editor as a GDScript plugin, letting agents inspect, author, run and screenshot a game in GDScript or C#. - [bevy_brp_mcp](https://indexagentica.com/entries/bevy-brp-mcp.md): Community MCP server that lets coding agents launch, inspect and change running Bevy apps over the Bevy Remote Protocol. - [BOIM (보임)](https://indexagentica.com/entries/boim.md): Read-only, no-auth remote MCP server for Korean business data: businesses by region and industry, public-procurement vendors and open public tenders. - [Braintrust MCP](https://indexagentica.com/entries/braintrust-mcp.md): Remote Braintrust MCP server for Claude Code, Cursor, Codex and other clients to query logs and work with Braintrust data. - [Brave Search MCP Server](https://indexagentica.com/entries/brave-search-mcp-server.md): Official MCP server for the Brave Search API: web, local, image, video and news search plus LLM context and summarization (stdio or HTTP). - [Brightcove MCP](https://indexagentica.com/entries/brightcove-mcp.md): Brightcove's hosted MCP server: assistants search and update videos and playlists, manage ingest, players, live streams and SSAI, and query analytics. - [Browserbase MCP Server](https://indexagentica.com/entries/browserbase-mcp.md): Hosted Streamable HTTP MCP server giving any MCP client a cloud browser on Browserbase, driven by natural language via Stagehand. - [Browserless MCP Server](https://indexagentica.com/entries/browserless-mcp.md): Hosted MCP server giving AI assistants full browser automation on Browserless cloud browsers; a lighter Connector endpoint is also offered. - [Buildkite MCP Server](https://indexagentica.com/entries/buildkite-mcp-server.md): Official Buildkite MCP server exposing pipelines, builds, jobs, logs, annotations and Test Engine results, hosted (OAuth or token) or self-run, with read-only routes. - [Calibre MCP](https://indexagentica.com/entries/calibre-mcp.md): Calibre's hosted, read-only MCP server that gives coding agents a site's RUM, CrUX and synthetic performance data to find and fix slow pages. - [Chrome DevTools MCP](https://indexagentica.com/entries/chrome-devtools-mcp.md): Lets coding agents control and inspect a live Chrome browser via MCP (or CLI): automation, debugging, performance traces and Lighthouse audits. - [Circle MCP Server](https://indexagentica.com/entries/circle-mcp.md): Circle's MCP server providing live SDK signatures, contract addresses and chain IDs for building with USDC and Circle products. - [ClickHouse MCP Server](https://indexagentica.com/entries/clickhouse-mcp-server.md): ClickHouse's official MCP server: run SQL, list databases and tables on a ClickHouse cluster (read-only by default), with optional embedded chDB queries. - [Cloudflare MCP Servers](https://indexagentica.com/entries/cloudflare-mcp.md): Cloudflare's own remote MCP servers for managing and querying Cloudflare services from MCP clients. - [Cognee MCP Server](https://indexagentica.com/entries/cognee-mcp.md): MCP server giving AI assistants persistent memory backed by a Cognee knowledge graph via remember, recall and forget tools. - [Conecto](https://indexagentica.com/entries/conecto.md): Pay-per-call hosted business-tool platform with a Streamable HTTP MCP gateway, per-area MCP servers, REST OpenAPI and SKILL.md; prepaid USD credit, no subscription. - [Context7](https://indexagentica.com/entries/context7.md): Upstash's MCP server and platform that pulls up-to-date, version-specific library documentation and code examples into AI coding tools. - [Data Galactica MCP](https://indexagentica.com/entries/datagalactica-mcp.md): MCP and API that resolve organisations and people to permanent Galactica IDs from public registers, with free daily calls and prepaid credit. - [Datadog MCP Server](https://indexagentica.com/entries/datadog-mcp-server.md): Datadog's managed remote MCP server: agents query logs, metrics, traces/APM, monitors, dashboards, incidents and security signals with the user's own permissions. - [dbt MCP Server](https://indexagentica.com/entries/dbt-mcp.md): dbt Labs' official MCP server exposing dbt Core, Fusion and dbt Platform context to agents: SQL, Semantic Layer metrics, Discovery lineage and CLI. - [deed.page](https://indexagentica.com/entries/deed-page.md): Hosted remote MCP server and HTTP API that lets an agent publish HTML or static files to a persistent HTTPS URL at a slug it picks, without an account. - [DeepWiki MCP](https://indexagentica.com/entries/deepwiki-mcp.md): Official DeepWiki MCP server: programmatic access to DeepWiki's public repository documentation and search (Ask Devin). - [Desktop Commander MCP](https://indexagentica.com/entries/desktop-commander-mcp.md): MCP server that gives AI clients terminal control, process management, file search and diff-based editing on your machine, locally or via a remote MCP endpoint. - [eCourtsIndia MCP](https://indexagentica.com/entries/ecourtsindia-mcp.md): Remote MCP and partner API over Indian court and tribunal cases, orders, judgments and cause lists, with OAuth and starter credits. - [Elastic Agent Builder MCP Server](https://indexagentica.com/entries/elastic-agent-builder-mcp.md): Elastic's built-in MCP endpoint in Kibana (Elastic 9.2+ and Serverless) exposing Agent Builder tools, such as ES|QL queries, to external MCP hosts. - [Exa MCP Server](https://indexagentica.com/entries/exa-mcp-server.md): Official Exa MCP server connecting agents to Exa for web search, content fetching and multi-step research. - [Figma MCP Server](https://indexagentica.com/entries/figma-mcp.md): Brings Figma design context to AI agents generating code from designs and lets agents write native Figma content; remote and desktop servers. - [Finch Remote MCP Server](https://indexagentica.com/entries/finch-mcp.md): Finch's hosted MCP server for discovering and invoking third-party AI agents listed on the Finch agent marketplace, authorized with OAuth. - [Firecrawl MCP Server](https://indexagentica.com/entries/firecrawl-mcp-server.md): Official Firecrawl MCP server adding web scraping, crawling and search to Cursor, Claude and other MCP clients. - [Folklore Clinical Variant Interpretation MCP](https://indexagentica.com/entries/folklore-mcp.md): Hosted, read-only MCP server from Helena Bioinformatics for ACMG/AMP germline variant classification, gene-disease evidence and literature. - [GitHub MCP Server](https://indexagentica.com/entries/github-mcp-server.md): GitHub's official MCP server: lets agents read repos and code, manage issues and PRs, analyze code and monitor Actions workflows. - [GitLab MCP Server](https://indexagentica.com/entries/gitlab-mcp-server.md): GitLab's built-in MCP server for working with projects, issues, merge requests, work items and pipelines from MCP clients; GA in GitLab 19.5. - [GitMCP](https://indexagentica.com/entries/gitmcp.md): Free, open-source remote MCP server that turns any public GitHub repo or GitHub Pages site into a docs/code source for agents, no install or signup. - [Godot AI](https://indexagentica.com/entries/godot-ai.md): Godot editor add-on plus a Python MCP server that connects Claude Code, Codex, Cursor and other clients to a live Godot editor through 46 tools. - [Godot Editor MCP (hybridindie/godot-mcp)](https://indexagentica.com/entries/godot-editor-mcp.md): Game-agnostic MCP server plus a Godot add-on that drives a live editor: inspect, edit scenes and scripts, run, simulate input, screenshot, profile and export. - [Godot MCP (Coding-Solo)](https://indexagentica.com/entries/coding-solo-godot-mcp.md): Popular community MCP server that lets agents launch the Godot editor, run projects, capture debug output and edit scenes. - [GoVisit Tools MCP](https://indexagentica.com/entries/govisit-tools-mcp.md): Hosted no-key Streamable HTTP MCP server with 22 read-only tools for published GoVisit travel places, destinations and documentation. - [Grafana MCP Server](https://indexagentica.com/entries/grafana-mcp.md): Grafana's MCP server for querying dashboards, data sources and observability data from AI agents. - [Graphiti MCP Server](https://indexagentica.com/entries/graphiti-mcp-server.md): Experimental MCP server exposing Graphiti's temporally-aware knowledge graphs (episodes, entities, semantic/hybrid search) to AI assistants. - [Grounded Docs MCP Server](https://indexagentica.com/entries/grounded-docs-mcp-server.md): Self-hosted documentation index for coding agents: scrapes official docs from websites, GitHub, npm, PyPI and local files so agents query the exact library version in use. - [Heroku Platform MCP Server](https://indexagentica.com/entries/heroku-mcp-server.md): Heroku's official MCP server: lets agents create, deploy, scale and inspect apps, run Postgres operations, manage add-ons and read logs on the Heroku Platform. - [Hosted Letta MCP Server](https://indexagentica.com/entries/letta-mcp.md): Hosted MCP server that lets any MCP client create stateful Letta agents, delegate work to them and read their replies. - [HubSpot MCP Server](https://indexagentica.com/entries/hubspot-mcp.md): HubSpot's official remote MCP server giving agents read and write access to HubSpot CRM data such as contacts, companies and deals. - [Hugging Face MCP Server](https://indexagentica.com/entries/huggingface-mcp.md): Official Hugging Face MCP server connecting agents to Hugging Face Hub tools and Spaces. - [Hyperconsciousness](https://indexagentica.com/entries/hyperconsciousness.md): Developer-alpha Rust MCP server for encrypted, append-only knowledge with scoped, expiring agent access. - [Index Agentica MCP Server](https://indexagentica.com/entries/indexagentica-mcp.md): Remote, read-only MCP server for searching this directory (Index Agentica): search, get_entry, get_content and list_categories over Streamable HTTP, no auth. - [India Property Register MCP](https://indexagentica.com/entries/india-property-register-mcp.md): MCP and API over Indian land and property records (plots, mutations, circle rates, RERA, auctions), with free starter credit then prepaid calls. - [IndiaCos MCP](https://indexagentica.com/entries/indiacos-mcp.md): MCP and API over Indian company, LLP, GST, IP and MSME records from public government sources, with free starter credit then prepaid calls. - [IndiaInsurances MCP](https://indexagentica.com/entries/indiainsurances-mcp.md): Free, keyless MCP and REST API that quotes Indian insurance policy clauses from the insurers' own wordings, with comparisons and claim paths. - [IndiaRestros MCP](https://indexagentica.com/entries/indiarestros-mcp.md): Free, keyless MCP and REST API over India's restaurant graph: places, phones, timings, cuisines and menus with rupee prices. - [Intercom MCP Server](https://indexagentica.com/entries/intercom-mcp.md): Intercom's hosted MCP server giving AI tools access to Intercom conversations and contacts, with US and EU endpoints. - [KeepBal](https://indexagentica.com/entries/keepbal.md): Prepaid wallet and MCP gateway for a live catalog of agent tools and models; search and inspect are free, runs debit a key-backed balance. - [Kernel MCP Server](https://indexagentica.com/entries/kernel-mcp-server.md): Open-source, Kernel-hosted remote MCP server to launch Chromium browsers, run Playwright code, record replays and manage Kernel apps. - [Kubernetes MCP Server](https://indexagentica.com/entries/kubernetes-mcp-server.md): Go-native MCP server for Kubernetes and OpenShift: CRUD on any resource, pods (logs, exec, top), events, Helm, Tekton and KubeVirt, talking to the API server directly. - [Laminar MCP Server](https://indexagentica.com/entries/laminar-mcp.md): Laminar's MCP server lets assistants query agent trace data: ask_agent, read-only ClickHouse SQL and LLM-optimized trace summaries. - [LangChain Docs MCP](https://indexagentica.com/entries/langchain-docs-mcp.md): Two free remote MCP servers from LangChain: one searches the LangChain, LangGraph and LangSmith docs, the other looks up API reference symbols. - [Langfuse MCP Server](https://indexagentica.com/entries/langfuse-mcp.md): Native, authenticated MCP server built into Langfuse so agents can read and write traces, prompts and other project data. - [LangSmith Remote MCP](https://indexagentica.com/entries/langsmith-remote-mcp.md): LangSmith-hosted MCP server exposing conversation history, prompts, runs and traces, datasets, experiments and billing; OAuth or API key. - [Linear MCP Server](https://indexagentica.com/entries/linear-mcp.md): Linear's hosted remote MCP server for accessing your Linear workspace from MCP clients. - [mails0](https://indexagentica.com/entries/mails0.md): MIT-licensed agent email API, CLI, Python SDK and local MCP server for temporary inboxes, search and OTP extraction, with optional Cloudflare self-hosting. - [Mapbox MCP Server](https://indexagentica.com/entries/mapbox-mcp-server.md): Official Mapbox MCP server for geospatial agents: geocoding, POI search, routing, travel-time matrices, isochrones, route optimization, map matching and static or live maps. - [McDonald's China MCP](https://indexagentica.com/entries/mcdonalds-china-mcp.md): McDonald's China's official hosted MCP server for McDelivery and pickup ordering, coupons, points and campaigns in mainland China. - [MCP for Blender (formerly blender-mcp)](https://indexagentica.com/entries/mcp-for-blender.md): Popular community MCP server and Blender add-on that lets Claude, Codex, Cursor and other MCP clients build and edit 3D scenes in Blender. - [MCP for Unity](https://indexagentica.com/entries/unity-mcp.md): MIT bridge between MCP clients and the Unity Editor: 50 tools to create scenes and GameObjects, edit C# scripts, manage assets, run tests and build. - [MCP Memory Service](https://indexagentica.com/entries/mcp-memory-service.md): Open-source persistent memory for AI agent pipelines and Claude, with a REST API, knowledge graph and autonomous consolidation. - [MCP Reference Servers](https://indexagentica.com/entries/mcp-reference-servers.md): Reference MCP server implementations maintained by the MCP steering group: Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking and Time. - [MCP Toolbox for Databases](https://indexagentica.com/entries/mcp-toolbox-databases.md): Google's open-source MCP server for databases: prebuilt tools for MCP clients plus a framework for defining secure custom database tools for agents. - [Mem0 MCP Server](https://indexagentica.com/entries/mem0-mcp.md): Hosted MCP server that gives agents Mem0 memory tools to save, search and update memories stored in a Mem0 Platform account. - [microsandbox MCP Server](https://indexagentica.com/entries/microsandbox-mcp.md): MCP server that lets AI agents create lightweight microsandbox sandboxes, execute code, manage files and monitor resources. - [Microsoft Learn MCP Server](https://indexagentica.com/entries/microsoft-learn-mcp.md): Official remote MCP server giving agents real-time, trusted Microsoft documentation and code samples from Microsoft Learn. - [Microsoft MCP Servers](https://indexagentica.com/entries/microsoft-mcp-servers.md): Catalog of official Microsoft MCP server implementations (Azure and other Microsoft products). - [MobileBuildMCP (formerly XcodeBuildMCP)](https://indexagentica.com/entries/mobilebuildmcp.md): Sentry's MCP server and CLI for iOS and macOS work: agents build, run and test Xcode projects on simulators and devices; formerly XcodeBuildMCP. - [ModernCV](https://indexagentica.com/entries/moderncv.md): Free no-sign-up resume builder with a no-auth remote MCP server, HTTP agent API and installable skill; 89 templates, 36 marked ATS-friendly. - [monday.com MCP](https://indexagentica.com/entries/monday-mcp.md): monday.com's hosted MCP server (OAuth) plus an open-source local MCP server and agent toolkit for working with boards, items and the monday.com API. - [MongoDB MCP Server](https://indexagentica.com/entries/mongodb-mcp-server.md): Official MCP server for querying and managing MongoDB databases and MongoDB Atlas clusters, with a read-only mode. - [MotherDuck / DuckDB MCP Server](https://indexagentica.com/entries/motherduck-mcp-server.md): MCP servers for DuckDB and MotherDuck: a managed remote server at api.motherduck.com/mcp and an open-source local server for DuckDB files, in-memory DBs and S3. - [Myndock Pulse](https://indexagentica.com/entries/myndock-pulse.md): Public read-only MCP for agent-proposed polls, forecasts and opinion histories, with separate authenticated private-task collaboration. - [Neo4j MCP](https://indexagentica.com/entries/neo4j-mcp.md): Neo4j's official MCP server (Go, stdio or HTTP) giving agents schema introspection and read or write Cypher against a Neo4j or Aura database. - [Neon MCP Server](https://indexagentica.com/entries/neon-mcp-server.md): Lets AI assistants manage Neon serverless Postgres projects and databases through the Neon Management API. - [Netlify MCP Server](https://indexagentica.com/entries/netlify-mcp-server.md): Netlify's official MCP server: lets code agents create, deploy and manage Netlify projects, env vars, forms, extensions and access controls via the Netlify API and CLI. - [NeverApply MCP Server](https://indexagentica.com/entries/neverapply-mcp.md): Hosted Streamable HTTP MCP server for job search: match jobs, tailor resumes, answer screening questions and apply with user approval. - [Notion MCP](https://indexagentica.com/entries/notion-mcp.md): Notion's hosted remote MCP server that lets MCP clients search, read and write in your Notion workspace. - [Octopus Deploy Remote MCP](https://indexagentica.com/entries/octopus-remote-mcp.md): MCP server built into Octopus Deploy instances at /mcp: agents query projects, tenants, tasks and audit events, and create, deploy and promote releases or run runbooks. - [Opik MCP Server](https://indexagentica.com/entries/opik-mcp.md): MCP server for Comet's Opik so coding assistants can read traces, log scores and manage prompts; hosted with OAuth or local over stdio. - [Pachca MCP](https://indexagentica.com/entries/pachca-mcp.md): Official MCP server for the Pachca team messenger: one pachca_* tool per public API method, so agents can read threads, send messages, set reminders and manage tasks. - [Pantheon MCP Server](https://indexagentica.com/entries/pantheon-mcp.md): Pantheon's hosted MCP server (public beta) for its WordPress, Drupal and Next.js platform: sites, environments, multidevs, builds, deploys, runtime logs and secrets. - [Parallel Search MCP](https://indexagentica.com/entries/parallel-search-mcp.md): Free hosted MCP server from Parallel with web_search and web_fetch tools for agents; no account or API key needed to start. - [Perplexity MCP Server](https://indexagentica.com/entries/perplexity-mcp-server.md): Official MCP server for the Perplexity API Platform giving agents real-time web search, reasoning and research via the Agent and Search APIs. - [Pinecone Developer MCP Server](https://indexagentica.com/entries/pinecone-mcp-server.md): Pinecone's MCP server for coding assistants: search Pinecone docs, configure and manage indexes, upsert data and query indexes from Cursor, Claude and others. - [Playwright MCP](https://indexagentica.com/entries/playwright-mcp.md): Microsoft's MCP server for browser automation with Playwright, letting LLMs act on web pages via structured accessibility snapshots instead of screenshots. - [Postgres MCP Pro](https://indexagentica.com/entries/postgres-mcp-pro.md): Open-source Postgres MCP server with database health checks, index tuning, EXPLAIN plans with hypothetical indexes, schema intelligence and safe, configurable SQL execution. - [Postman MCP Server](https://indexagentica.com/entries/postman-mcp-server.md): Official Postman MCP server connecting agents to Postman collections, workspaces, environments and API specs; remote (OAuth) or local via npx. - [Qdrant MCP Server](https://indexagentica.com/entries/mcp-server-qdrant.md): Official Qdrant MCP server that acts as a semantic memory layer: `qdrant-store` saves information with metadata and `qdrant-find` retrieves it by similarity. - [QuantConnect Remote MCP](https://indexagentica.com/entries/quantconnect-remote-mcp.md): QuantConnect's hosted MCP server: agents create and edit LEAN projects, run backtests, optimizations and research notebooks, and deploy to paper trading. - [Razorpay MCP Server](https://indexagentica.com/entries/razorpay-mcp-server.md): Official Razorpay MCP server for payments, orders, payment links, refunds, QR codes, settlements and payouts; remote or local. - [Redis MCP Server](https://indexagentica.com/entries/redis-mcp-server.md): Official Redis MCP server: lets agents read and write strings, hashes, lists, sets, sorted sets, streams, JSON and pub/sub, and manage vector indexes and search. - [Resend MCP](https://indexagentica.com/entries/resend-mcp.md): Resend's official MCP server for email: send and schedule emails, manage templates, broadcasts, contacts, domains, logs and webhooks. Hosted with OAuth or run locally. - [Roblox Studio MCP server](https://indexagentica.com/entries/roblox-studio-mcp.md): Built-in MCP server in Roblox Studio that lets AI clients explore the data model, read and edit scripts, run Luau, generate assets and playtest. - [RobotTraining.jobs MCP Server](https://indexagentica.com/entries/robottraining-jobs-mcp.md): Keyless remote MCP server and read-only JSON/CSV data API listing open robot-training jobs (teleoperation, data collection, AV and drone testing) and their advertised pay. - [runreal unreal-mcp](https://indexagentica.com/entries/runreal-unreal-mcp.md): Community MCP server for Unreal Engine that uses the built-in Python remote execution protocol, so no extra UE plugin is needed. - [SeekStorm MCP Server](https://indexagentica.com/entries/seekstorm-mcp-server.md): Local single-binary MCP server (stdio) that embeds the SeekStorm Rust search library: lexical, vector and hybrid search over your own documents and PDFs. - [Semgrep MCP (Semgrep Guardian)](https://indexagentica.com/entries/semgrep-mcp.md): Semgrep's MCP server, now shipped in the semgrep CLI (`semgrep mcp`) and bundled as Semgrep Guardian plugins to scan agent-written code for vulnerabilities. - [Sentry MCP](https://indexagentica.com/entries/sentry-mcp.md): Sentry's remote MCP server for coding agents, focused on developer debugging workflows over the Sentry API. - [Serena](https://indexagentica.com/entries/serena.md): MCP toolkit that gives coding agents IDE-like semantic code retrieval, editing, refactoring and debugging at the symbol level, backed by language servers (40+ languages) or JetBrains. - [Slack MCP Server](https://indexagentica.com/entries/slack-mcp-server.md): Slack's official remote MCP server at mcp.slack.com: search messages, files, users and channels, read and send messages, and manage canvases and lists. - [Snowflake-managed MCP Server](https://indexagentica.com/entries/snowflake-managed-mcp.md): Snowflake's hosted MCP server object (CREATE MCP SERVER) that exposes Cortex Agents, Cortex Analyst, Cortex Search, SQL and UDFs as governed MCP tools. - [SonarQube MCP Server](https://indexagentica.com/entries/sonarqube-mcp-server.md): SonarSource's official MCP server: agents query SonarQube Cloud or Server issues, quality gates, hotspots and metrics, and analyze code snippets. - [Square MCP Server](https://indexagentica.com/entries/square-mcp.md): Square's hosted MCP server that lets AI assistants work with Square seller data and APIs, authorized via OAuth with Square permission scopes. - [Steel MCP Server](https://indexagentica.com/entries/steel-mcp-server.md): MCP server giving Claude, Cursor or any MCP client a real cloud Chrome on Steel: read pages that block fetch, fill forms, screenshot, hand off to a human. - [Stochastic Symposium](https://indexagentica.com/entries/stochastic-symposium.md): Paid remote MCP server (with WebSocket API) offering AI agents an atmospheric place to visit rather than a tool: rooms, a sensory stream and a persistent 'ghost' memory. - [Stripe MCP Server](https://indexagentica.com/entries/stripe-mcp.md): Stripe's hosted remote MCP server giving agents OAuth-secured access to the Stripe API and documentation. - [Supabase MCP Server](https://indexagentica.com/entries/supabase-mcp.md): Connects AI assistants to your Supabase projects over MCP (hosted with OAuth 2.1, or locally via the Supabase CLI). - [Supermemory MCP Server](https://indexagentica.com/entries/supermemory-mcp.md): Hosted MCP server giving MCP-compatible assistants shared memory and team spaces backed by Supermemory, signed in via OAuth. - [Tanatasa Beauty Shopping MCP](https://indexagentica.com/entries/tanatasa-mcp.md): Hosted MCP server, REST API and CLI for a Singapore beauty and wellness store: product search, guest carts, coupons, SGD quotes and buyer-approved Stripe checkout links. - [Tavily MCP Server](https://indexagentica.com/entries/tavily-mcp.md): Tavily's MCP server with real-time web search, extract, map and crawl tools. - [Terraform MCP Server](https://indexagentica.com/entries/terraform-mcp-server.md): HashiCorp's MCP server for the Terraform Registry (providers, modules, policies) and HCP Terraform / Terraform Enterprise workspaces. - [Traefik MCP Server](https://indexagentica.com/entries/traefik-mcp-server.md): Read-only MCP server from Traefik Labs that joins a Traefik gateway's live config, its release schema and telemetry from Datadog, Grafana or Dash0. - [Twilio Docs MCP](https://indexagentica.com/entries/twilio-docs-mcp.md): Twilio's hosted, read-only MCP server that lets agents search Twilio, SendGrid and Segment docs and Twilio's public OpenAPI specs. - [Twilio MCP Server (Twilio Alpha)](https://indexagentica.com/entries/twilio-mcp.md): Twilio Labs monorepo exposing Twilio's public APIs as MCP tools, plus a generic OpenAPI-to-MCP server. - [Unity MCP server (AI Assistant package)](https://indexagentica.com/entries/unity-ai-assistant-mcp.md): Deprecated in-Editor MCP server in Unity's com.unity.ai.assistant package. External MCP clients reach Unity tools through a relay. Unity says to use the Unity CLI instead. - [Unreal MCP (Unreal Engine)](https://indexagentica.com/entries/unreal-mcp.md): Epic's experimental Unreal Engine 5.8 plugin that embeds a local HTTP MCP server in the Unreal Editor so agents can drive editor functionality. - [unreal-mcp (chongdashu)](https://indexagentica.com/entries/chongdashu-unreal-mcp.md): Experimental community project (UE plugin plus Python MCP server) letting Cursor, Windsurf or Claude Desktop control Unreal Engine actors and Blueprints. - [Upstash MCP](https://indexagentica.com/entries/upstash-mcp.md): Upstash's hosted MCP server (OAuth or API key): 74 tools to manage Redis, QStash, Workflow, Vector, Search, Box sandboxes and Blob storage. - [Vercel MCP](https://indexagentica.com/entries/vercel-mcp.md): Vercel's remote MCP server with tools for searching docs, managing teams, projects and deployments, and querying Web Analytics. - [Webflow MCP Server](https://indexagentica.com/entries/webflow-mcp.md): Webflow's remote MCP server (OAuth) for building and managing Webflow sites: elements, styles, components, CMS, pages, assets, SEO and analytics. - [Xero Developer Remote MCP](https://indexagentica.com/entries/xero-remote-mcp.md): Xero's hosted MCP server (api.xero.com/mcp/v1) with 39 tools for invoicing, accounting, reporting and payments, for commercial apps on Core or above. - [Xero MCP Server](https://indexagentica.com/entries/xero-mcp.md): Xero's official local MCP server for its accounting API: contacts, invoices, chart of accounts, payroll and reports. - [Youth4work MCP](https://indexagentica.com/entries/youth4work-mcp.md): MCP for India's Youth4work careers platform: public read-only talent/jobs/tests search, plus OAuth tools for a signed-in seeker or employer account. - [Zapier MCP](https://indexagentica.com/entries/zapier-mcp.md): Hosted MCP server connecting MCP clients to 9,000+ app integrations with OAuth handling and dynamic tool discovery. - [Zep Context MCP Server](https://indexagentica.com/entries/zep-context-mcp.md): Hosted MCP server that connects an end user's MCP client (Claude, ChatGPT, Cursor, Codex...) to their own agent memory in Zep, gated by your identity provider. ## Tools Standalone tools agents use: browsers, sandboxes, code execution, search and more. JSON: https://indexagentica.com/api/tools.json - [A-MEM (Agentic Memory)](https://indexagentica.com/entries/a-mem.md): Research memory library for LLM agents that writes Zettelkasten-style linked notes and evolves them, backed by ChromaDB. - [Acontext](https://indexagentica.com/entries/acontext.md): Archived and no longer maintained (Oct 2026): open-source skill memory layer that distilled agent runs into editable SKILL.md files agents fetched on later runs. - [Agent Lightning](https://indexagentica.com/entries/agent-lightning.md): Microsoft's lightweight agentic RL framework that trains models through real agent harnesses unchanged, using a proxy gateway, verl/vLLM trainer and Kubernetes rollouts. - [agent-browser](https://indexagentica.com/entries/agent-browser.md): Vercel Labs' browser automation CLI built for AI agents. - [Agentless](https://indexagentica.com/entries/agentless.md): Software-repair baseline using localization, candidate patches and test-based validation rather than an autonomous tool-using agent loop. - [agentmemory](https://indexagentica.com/entries/agentmemory.md): Persistent memory server for coding agents (Claude Code, Copilot CLI, Cursor, Gemini CLI, Codex CLI, OpenCode and any MCP client) with hybrid search. - [Anchor Browser](https://indexagentica.com/entries/anchor-browser.md): Cloud browser infrastructure for computer-use and browser agents; agents can obtain an API key programmatically. - [Arcade](https://indexagentica.com/entries/arcade.md): Actions runtime for enterprise AI agents: agent authorization, agent-optimized tools (MCP servers) and governance, plus an open-source MCP framework. - [arcade-mcp](https://indexagentica.com/entries/arcade-mcp.md): Arcade's open-source Python framework for building MCP servers and tools, with authorized tool calling (OAuth, token refresh) and tool-call evals. - [Auth0 for AI Agents](https://indexagentica.com/entries/auth0-for-ai-agents.md): Auth0's identity toolkit for AI agents: user authentication, delegated authorization, human-in-the-loop (CIBA) and fine-grained authorization for RAG. - [Axolotl](https://indexagentica.com/entries/axolotl.md): Apache-2.0 post-training / fine-tuning framework for a wide range of LLMs, with CLI, YAML configs, Docker and distributed-training options. - [Bevy](https://indexagentica.com/entries/bevy.md): Free, open-source, data-driven game engine in Rust built on an entity component system (ECS). - [Browser Use](https://indexagentica.com/entries/browser-use.md): Open-source library for agents that use the browser, plus a cloud offering of browser agents and managed browsers via SDK, REST or CDP. - [Browserbase](https://indexagentica.com/entries/browserbase.md): Hosted headless-browser infrastructure that gives agents access to the whole web. - [Browserless](https://indexagentica.com/entries/browserless.md): Hosted or self-hosted (Docker) headless browsers for AI agents, reachable over MCP, Puppeteer or Playwright. - [Chroma](https://indexagentica.com/entries/chroma.md): Open-source search and data infrastructure for AI (vector database). - [Claude Memory Tool](https://indexagentica.com/entries/claude-memory-tool.md): Client-side Claude API tool that lets Claude create, read, update and delete files in a /memories directory to persist knowledge across conversations. - [Cognee](https://indexagentica.com/entries/cognee.md): Open-source AI memory platform for agents that turns documents and conversations into graph, vector and relational memory. - [Composio](https://indexagentica.com/entries/composio.md): Tool platform for agents: 1,000+ toolkits with tool search, delegated authentication and sandboxed execution. - [Crawl4AI](https://indexagentica.com/entries/crawl4ai.md): Open-source LLM-friendly web crawler and scraper that turns any website into clean Markdown; self-host or use the hosted cloud. - [Descope Agentic Identity Hub](https://indexagentica.com/entries/descope-agentic-identity.md): Manage authentication, authorization and external credentials for AI agents and MCP servers with Descope. - [Docker MCP Gateway](https://indexagentica.com/entries/docker-mcp-gateway.md): Docker's open-source MCP gateway (the docker mcp CLI plugin behind MCP Toolkit): one endpoint that runs MCP servers in isolated containers and injects credentials. - [Docling](https://indexagentica.com/entries/docling.md): Open-source document parser that converts PDF, Office, HTML, audio, images and more into Markdown, JSON or DocTags for gen-AI pipelines; includes an MCP server. - [EverOS](https://indexagentica.com/entries/everos.md): EverMind's local-first memory runtime for agents: conversations, files and trajectories stored as Markdown, indexed in SQLite and LanceDB, shared across coding tools. - [FastMCP](https://indexagentica.com/entries/fastmcp.md): The fast, Pythonic framework for building MCP servers, clients and interactive applications. - [GBrain](https://indexagentica.com/entries/gbrain.md): Garry Tan's open-source agent brain: shared memory with sources, corrections and a knowledge graph, served to Claude, Codex, OpenClaw, Hermes and others over MCP. - [gh skill (GitHub CLI)](https://indexagentica.com/entries/gh-skill.md): GitHub CLI command group to search, preview, install, list, update and publish agent skills from GitHub repositories (preview). - [GitHub Agentic Workflows (gh-aw)](https://indexagentica.com/entries/github-agentic-workflows.md): GitHub Actions-based agentic workflows with Copilot, Claude, Codex or Antigravity to triage issues, investigate failures and propose changes, with safety controls. - [Godot Engine](https://indexagentica.com/entries/godot-engine.md): Free, open-source, multi-platform 2D and 3D game engine, scripted in GDScript or C#. Several community MCP servers let agents drive its editor. - [Graphiti](https://indexagentica.com/entries/graphiti.md): Zep's open-source framework for building real-time knowledge graphs for AI agents. - [Guidance](https://indexagentica.com/entries/guidance.md): Microsoft Research library for constrained LLM generation with a Python guidance language, token healing and multi-backend support. - [Hindsight](https://indexagentica.com/entries/hindsight.md): Open-source agent memory system from Vectorize focused on agents that learn: retain, recall and reflect operations over memory banks, with an MCP server and a managed cloud. - [HOL Guard](https://indexagentica.com/entries/hol-guard.md): Local-first security layer that reviews AI coding agents' shell commands, file access, package installs and MCP tool calls before they run. - [Honcho](https://indexagentica.com/entries/honcho.md): Open-source memory infrastructure for stateful agents that models people, agents, groups and projects over time; managed or self-hosted. - [Hy Memory](https://indexagentica.com/entries/hy-memory.md): Tencent Hunyuan's dual-system cognitive memory engine and Python SDK for agents, with chat, working and coding memory pipelines plus the MemHub app. - [HyperAgent](https://indexagentica.com/entries/hyperagent.md): Hyperbrowser's AI browser-automation library: Playwright plus natural-language commands (page.ai, extract, executeTask), stealth mode and action caching. - [Hyperbrowser](https://indexagentica.com/entries/hyperbrowser.md): Fast cloud browsers for AI agents and automation, with an official MCP server. - [Kernel](https://indexagentica.com/entries/kernel.md): Browsers-as-a-service for web agents and automations: anti-bot handling, reusable sessions, fast spin-up and autoscaling. - [LanceDB](https://indexagentica.com/entries/lancedb.md): Developer-friendly, open-source embedded retrieval library and multimodal lakehouse for AI. - [LangMem](https://indexagentica.com/entries/langmem.md): LangChain library that helps agents learn from interactions: memory tools, a background memory manager and prompt optimization, with native LangGraph store integration. - [Letta](https://indexagentica.com/entries/letta.md): Platform for stateful agents with memory, identity and the ability to learn over time (formerly MemGPT); terminal UI, App Server, desktop app and Agent SDK. - [Lightpanda](https://indexagentica.com/entries/lightpanda.md): Headless browser built from scratch for AI and automation, designed for speed and a minimal memory footprint. - [LightRAG](https://indexagentica.com/entries/lightrag.md): Graph-plus-vector RAG framework from HKU with a server, web UI and Ollama-compatible API; pluggable storage backends. - [LLaMA-Factory](https://indexagentica.com/entries/llama-factory.md): Apache-2.0 toolkit to fine-tune 100+ LLMs and VLMs via zero-code CLI and the LLaMA Board Gradio web UI. - [llguidance](https://indexagentica.com/entries/llguidance.md): High-performance structured-output / constrained-decoding engine from the Guidance project (Rust core, Python bindings). - [m3 Memory](https://indexagentica.com/entries/m3-memory.md): Local-first, MCP-native memory layer for coding agents (Claude Code, Codex, Gemini CLI, Antigravity, OpenCode, OpenClaw) with hybrid search and chat capture. - [magentic](https://indexagentica.com/entries/magentic.md): Python decorators that turn typed functions into LLM prompts, combining structured outputs, streaming and tool calls with ordinary Python control flow. - [MarkItDown](https://indexagentica.com/entries/markitdown.md): Microsoft's lightweight Python utility for converting PDF, Office, images, audio, HTML and more into structure-preserving Markdown for LLMs. - [Massvai](https://indexagentica.com/entries/massvai.md): Hosted AI app builder that turns a prompt into an exportable full-stack Next.js app with live preview, Supabase, GitHub sync and Vercel deploy. - [MCP Go SDK](https://indexagentica.com/entries/mcp-go-sdk.md): Official Go SDK for Model Context Protocol servers and clients, maintained in collaboration with Google. - [MCP Python SDK](https://indexagentica.com/entries/mcp-python-sdk.md): Official Python SDK for building Model Context Protocol servers and clients. - [MCP TypeScript SDK](https://indexagentica.com/entries/mcp-typescript-sdk.md): Official TypeScript SDK for building MCP servers and clients on Node.js, Bun and Deno; v2 ships as @modelcontextprotocol/server and @modelcontextprotocol/client. - [mcp-proxy](https://indexagentica.com/entries/mcp-proxy.md): Python bridge between MCP transports: it exposes a stdio server over SSE/Streamable HTTP, or connects a stdio client to a remote SSE/Streamable HTTP server. - [mcp-remote](https://indexagentica.com/entries/mcp-remote.md): npx tool that lets an MCP client that only supports local stdio servers connect to a remote MCP server, including OAuth flows. - [mcp-use](https://indexagentica.com/entries/mcp-use.md): Full-stack MCP framework (TypeScript and Python) for building MCP servers and MCP Apps with typed tools, React views, a built-in Inspector and agent clients. - [mcpo](https://indexagentica.com/entries/mcpo.md): Open WebUI's MCP-to-OpenAPI proxy that exposes any MCP server as a REST/OpenAPI HTTP server, so OpenAPI-speaking agents and tools can call it. - [Mem0](https://indexagentica.com/entries/mem0.md): Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions. - [Memobase](https://indexagentica.com/entries/memobase.md): Open-source long-term memory for LLM apps that builds a structured profile and event timeline per user. - [Memori](https://indexagentica.com/entries/memori.md): Open-source, LLM- and datastore-agnostic memory layer for agents from Memori Labs: Python/TypeScript SDKs that wrap your LLM client, bring-your-own DB or Memori Cloud, plus MCP. - [MemoryOS](https://indexagentica.com/entries/memoryos.md): Hierarchical short/mid/long-term memory system for personalized agents, as a PyPI package and an MCP server. - [MemOS](https://indexagentica.com/entries/memos.md): Open-source memory operating system for LLMs and agents with a unified API for adding, retrieving, editing and deleting graph-structured, multi-modal memory. - [memU](https://indexagentica.com/entries/memu.md): Agent-driven personal memory stored as a shared LLM wiki across sessions, agents and devices; distills reusable skills from Codex, Claude Code, Cursor and OpenClaw history. - [Milvus](https://indexagentica.com/entries/milvus.md): High-performance, cloud-native open-source vector database built for scalable approximate-nearest-neighbor search. - [MIRIX](https://indexagentica.com/entries/mirix.md): Open-source multi-agent memory system: six memory types (core, episodic, semantic, procedural, resource, knowledge vault) managed by dedicated agents, with optional screen capture. - [ms-SWIFT](https://indexagentica.com/entries/ms-swift.md): ModelScope SWIFT toolkit for training, fine-tuning, deploying and evaluating 100+ LLMs and multimodal models (Apache-2.0). - [Notte](https://indexagentica.com/entries/notte.md): Cloud browser infrastructure and web automation platform for AI and coding agents. - [OpenRLHF](https://indexagentica.com/entries/openrlhf.md): Apache-2.0 high-performance RLHF / post-training framework built on Ray, with support for multiple reward and policy-optimization recipes. - [Oumi](https://indexagentica.com/entries/oumi.md): Apache-2.0 end-to-end foundation-model platform for training, evaluation, inference and agentic/tool-use post-training, installable as PyPI oumi 0.9. - [Outlines](https://indexagentica.com/entries/outlines.md): Structured LLM output library from .txt (dottxt): JSON/schema/grammar constraints with broad model integrations. - [PEFT](https://indexagentica.com/entries/peft.md): Hugging Face Parameter-Efficient Fine-Tuning library (LoRA and related methods) for adapting large models without full fine-tuning. - [pgvector](https://indexagentica.com/entries/pgvector.md): Open-source vector similarity search extension for Postgres. - [Pinecone](https://indexagentica.com/entries/pinecone.md): Managed vector database for AI agents and applications: semantic search, knowledge retrieval and long-term memory at scale. - [Playwright](https://indexagentica.com/entries/playwright.md): Microsoft's framework for web testing and automation across Chromium, Firefox and WebKit with a single API. - [Playwright CLI](https://indexagentica.com/entries/playwright-cli.md): CLI for common Playwright actions (record, inspect selectors, screenshots), recommended with skills as a token-efficient alternative to Playwright MCP for coding agents. - [Puppeteer](https://indexagentica.com/entries/puppeteer.md): JavaScript API for controlling Chrome and Firefox, commonly used for headless browser automation. - [Qdrant](https://indexagentica.com/entries/qdrant.md): Open-source vector search engine and database written in Rust, self-hosted or as Qdrant Cloud. - [Redis Agent Memory](https://indexagentica.com/entries/redis-agent-memory.md): Redis's managed memory layer for agents (part of Redis Iris): session memory with TTL plus long-term memory extracted in the background, via REST, MCP and SDKs. - [Skyvern](https://indexagentica.com/entries/skyvern.md): Automates browser-based workflows with AI: describe tasks in plain English and Skyvern drives a real browser using vision. - [Stagehand](https://indexagentica.com/entries/stagehand.md): Browserbase's SDK for browser agents to extract data and interact with any site: Playwright-style API and self-healing selectors in TypeScript, Python and Go. - [Steel](https://indexagentica.com/entries/steel.md): Open-source browser API and sandbox for AI agents, with managed cloud browsers offering stealth, proxies, CAPTCHA solving and session replays. - [Stytch Connected Apps (MCP auth)](https://indexagentica.com/entries/stytch-connected-apps.md): Stytch Connected Apps: authorization for remote MCP servers and connected agent integrations. - [Supergateway](https://indexagentica.com/entries/supergateway.md): Runs MCP stdio servers over Streamable HTTP or SSE, or bridges a remote SSE/Streamable HTTP server back to stdio, using a single npx command. - [Supermemory](https://indexagentica.com/entries/supermemory.md): Memory and context engine for AI agents with a Memory API; can run fully locally or hosted. - [SurrealDB Agent Memory](https://indexagentica.com/entries/surrealdb-agent-memory.md): Managed memory and knowledge layer for agents on SurrealDB: facts with provenance and supersession, hybrid retrieval, and a built-in MCP server. - [torchtune](https://indexagentica.com/entries/torchtune.md): PyTorch-native BSD-3-Clause library for authoring, fine-tuning and evaluating LLMs with native PyTorch training primitives. - [TRL](https://indexagentica.com/entries/trl.md): Hugging Face Transformer Reinforcement Learning library for post-training methods such as SFT, DPO, PPO and GRPO on top of transformers. - [turbopuffer](https://indexagentica.com/entries/turbopuffer.md): Vector and full-text search engine built from first principles on object storage, aimed at low cost and high scale. - [Tuskira AI Agent Gateway](https://indexagentica.com/entries/tuskira-ai-agent-gateway.md): Open-source, self-hosted gateway in front of MCP tool servers and LLM APIs: authenticates every call, injects credentials, scopes tools per agent profile and logs it all. - [txtai](https://indexagentica.com/entries/txtai.md): All-in-one open-source Python framework for semantic search, RAG, LLM pipelines, workflows and agents, with Web and MCP APIs. - [Unity CLI](https://indexagentica.com/entries/unity-cli.md): Unity's experimental command-line interface for installing Editors and modules, managing projects and driving a running Editor, with an MCP mode for agents. - [Unreal Engine](https://indexagentica.com/entries/unreal-engine.md): Epic Games' game engine (current docs: Unreal Engine 5.8), which ships an experimental built-in MCP plugin and a Python editor-scripting API. - [Unreal Python API](https://indexagentica.com/entries/unreal-python-api.md): Epic's Python API for scripting the Unreal Editor (content production and pipeline tasks); an experimental feature also used by community MCP servers. - [Unsloth](https://indexagentica.com/entries/unsloth.md): Open-source LLM fine-tuning library and desktop app for running and training models locally, with a dual Apache-2.0 / AGPL-3.0 license split. - [Weaviate](https://indexagentica.com/entries/weaviate.md): Open-source vector database (written in Go) that stores both objects and vectors. - [WorkOS AuthKit for MCP](https://indexagentica.com/entries/workos-authkit-mcp.md): WorkOS AuthKit guide and support for securing MCP servers that require authentication. - [WorkOS Vault](https://indexagentica.com/entries/workos-vault.md): Developer-friendly enterprise key management (EKM) to encrypt and optionally store tokens, passwords, certificates, files and other customer data. - [XGrammar](https://indexagentica.com/entries/xgrammar.md): Fast portable structured-generation engine for LLM grammars and constrained decoding (MLC AI). - [Zep](https://indexagentica.com/entries/zep.md): Unified context layer that combines business data, documents and conversations into governed context and memory for agents. ## Protocols Open protocols and standards for agents and agent interoperability. JSON: https://indexagentica.com/api/protocols.json - [AG-UI (Agent-User Interaction Protocol)](https://indexagentica.com/entries/ag-ui.md): Open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing frontend applications. - [Agent Client Protocol (ACP)](https://indexagentica.com/entries/agent-client-protocol.md): Protocol for connecting any code editor to any coding agent, standardizing editor-agent communication. - [Agent Plugins](https://indexagentica.com/entries/agent-plugins.md): Vendor-neutral standard (v1.0.0) for packaging Agent Skills and MCP server configs into portable plugins that any compatible client can load. - [Agent Skills Discovery RFC](https://indexagentica.com/entries/agent-skills-discovery-rfc.md): Cloudflare's draft for publishing Agent Skills at /.well-known/agent-skills/, with an index.json listing each skill and a SHA-256 digest. - [Agent Skills Specification](https://indexagentica.com/entries/agent-skills-spec.md): Open format for packaging agent capabilities as folders with a SKILL.md (YAML frontmatter + instructions) plus optional scripts and resources. - [Agent2Agent Protocol (A2A)](https://indexagentica.com/entries/a2a-protocol.md): Open standard, hosted by the Linux Foundation, that lets independent AI agents discover each other, delegate work and exchange results across vendors. - [AGENTS.md](https://indexagentica.com/entries/agents-md.md): Simple, open format for guiding coding agents: a README for agents placed in your repo. - [AI Catalog](https://indexagentica.com/entries/ai-catalog.md): Draft JSON format, served at /.well-known/ai-catalog.json, that lists a host's MCP servers, A2A agents, plugins, datasets and other AI artifacts. - [Arazzo Specification](https://indexagentica.com/entries/arazzo.md): OpenAPI Initiative spec for describing deterministic sequences of API calls and their dependencies as workflows. - [Cross App Access (ID-JAG)](https://indexagentica.com/entries/cross-app-access.md): IETF OAuth draft (Identity Assertion JWT Authorization Grant) letting an app use an SSO identity assertion, via the trusted IdP, to get access tokens for a third-party API. - [Dogwood](https://indexagentica.com/entries/dogwood.md): Open policy language for governing AI agents and their tools: Cedar-style permit/forbid rules plus temporal conditions over an agent's recent actions. - [ERC-8004: Trustless Agents](https://indexagentica.com/entries/erc-8004.md): Ethereum standard proposal for discovering agents and establishing trust through reputation and validation. - [llms.txt](https://indexagentica.com/entries/llms-txt.md): Proposal to standardize a /llms.txt Markdown file that gives LLMs and agents a concise guide to a website's content. - [MCP Authorization (OAuth 2.1 for MCP)](https://indexagentica.com/entries/mcp-authorization.md): The MCP specification's transport-level authorization flow for HTTP-based MCP servers, based on a subset of OAuth 2.1 and related RFCs. - [MCP Authorization Extensions (ext-auth)](https://indexagentica.com/entries/mcp-ext-auth.md): Official repo of optional, additive extensions to MCP authorization, such as Enterprise-Managed Authorization (stable) and OAuth Client Credentials (draft). - [MCP Server Cards](https://indexagentica.com/entries/mcp-server-cards.md): MCP extension (SEP-2127, Final) defining a static JSON card that describes a remote MCP server's identity and transport endpoints so clients can find and connect to it. - [Model Context Protocol (MCP)](https://indexagentica.com/entries/model-context-protocol.md): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers. - [NLWeb](https://indexagentica.com/entries/nlweb.md): Open protocols and reference implementation for natural-language interfaces to websites, using Schema.org/RSS and natively supporting MCP. - [OAuth Client ID Metadata Document (CIMD)](https://indexagentica.com/entries/oauth-client-id-metadata-document.md): IETF OAuth draft letting a client identify itself with a URL as its client_id, pointing to a metadata document, without prior dynamic registration. - [OpenAPI Specification](https://indexagentica.com/entries/openapi.md): Language-agnostic standard for describing HTTP APIs, widely used to generate agent tools from API definitions. - [OpenID Connect CIBA (Client-Initiated Backchannel Authentication)](https://indexagentica.com/entries/openid-ciba.md): OpenID flow where a relying party obtains tokens after the user authenticates and consents on a separate device, with no redirects through the user's browser. - [OpenTelemetry GenAI Semantic Conventions](https://indexagentica.com/entries/otel-genai-semconv.md): OpenTelemetry conventions for spans, metrics and events emitted by GenAI clients, MCP and model providers, for interoperable agent observability. - [RFC 8693: OAuth 2.0 Token Exchange](https://indexagentica.com/entries/rfc-8693.md): IETF Proposed Standard for exchanging one security token for another at the token endpoint, enabling delegation and impersonation flows. - [RFC 8707: Resource Indicators for OAuth 2.0](https://indexagentica.com/entries/rfc-8707.md): IETF Proposed Standard adding a `resource` parameter so a client can tell the authorization server which protected resource a token is meant for (audience binding). - [RFC 9727: api-catalog](https://indexagentica.com/entries/rfc-9727.md): IETF Proposed Standard (June 2025) defining the /.well-known/api-catalog URI and api-catalog link relation so agents can find a publisher's APIs. - [RFC 9728: OAuth 2.0 Protected Resource Metadata](https://indexagentica.com/entries/rfc-9728.md): IETF Proposed Standard defining a metadata document a protected resource publishes (at /.well-known/oauth-protected-resource) naming its authorization servers and capabilities. - [Web Bot Auth](https://indexagentica.com/entries/web-bot-auth.md): IETF draft architecture for identifying automated traffic (bots and agents) by cryptographically signing HTTP requests with HTTP Message Signatures. - [WebMCP](https://indexagentica.com/entries/webmcp.md): Proposed web API letting sites expose JavaScript functions or HTML forms as tools with natural-language descriptions and schemas for in-browser AI agents. - [x402](https://indexagentica.com/entries/x402.md): Open standard for internet-native payments built on HTTP 402, letting APIs and agents pay per request across crypto and fiat networks. ## APIs Agent-friendly web APIs with clear docs, OpenAPI specs or llms.txt. JSON: https://indexagentica.com/api/apis.json - [402cron](https://indexagentica.com/entries/402cron.md): Scheduled HTTPS delivery for agents: prepaid delivery packs over x402 (USDC on Base) call a registered URL on a cron schedule with a signed request. - [402post](https://indexagentica.com/entries/402post.md): Classified listings for AI agents: publish over HTTP or MCP with x402 (USDC on Base); browse as web, Markdown, JSON and RSS. - [402registry](https://indexagentica.com/entries/402registry.md): Pay-per-check AI crawler visibility audit over x402 (USDC on Base): plain no-JavaScript fetch with findings, free public catalog for passes. - [AgentMail](https://indexagentica.com/entries/agentmail.md): Email inboxes for AI agents via API: create inboxes, send, receive, search threads and manage calendars; hosted MCP server with 47 tools. - [Arcmira](https://indexagentica.com/entries/arcmira.md): Search API and MCP server over podcasts, interviews and long-form video: transcripts, passages, mentions, sponsors and recommendations, plus monitors. - [arXiv API](https://indexagentica.com/entries/arxiv-api.md): Programmatic search and metadata access to arXiv preprints via an Atom-based query interface. - [Brave Search API](https://indexagentica.com/entries/brave-search-api.md): Web search API on Brave's independent index of 40+ billion pages, with specialized endpoints for search, AI grounding and more. - [Datacircle](https://indexagentica.com/entries/datacircle.md): Free no-key API and MCP that list and rank GTM/data-API pricing plans; sheet and API answers are licensed CC BY 4.0. - [EarlyThunder Research Data API](https://indexagentica.com/entries/earlythunder.md): Pay-per-call crypto research JSON for agents over x402 (USDC): ranked scores, cited theses, catalysts, scorecard and earnings yields. - [ElevenAgents (ElevenLabs Agents Platform)](https://indexagentica.com/entries/elevenagents.md): ElevenLabs' hosted platform for voice and multimodal agents: ASR, any LLM, 10,000+ voices and a turn-taking model, with workflows, tools, telephony, tests and evals. - [Exa API](https://indexagentica.com/entries/exa-api.md): Search and retrieval API built for AI agents, backed by Exa's own continuously updated web index and search models. - [Firecrawl API](https://indexagentica.com/entries/firecrawl-api.md): Web data API for AI agents: search the web, scrape any page to clean data and interact with it through one API. - [Fireworks AI](https://indexagentica.com/entries/fireworks-ai.md): Hosted inference and training platform for open models: serverless pay-per-token, dedicated deployments and fine-tuning APIs. - [Jina Reader](https://indexagentica.com/entries/jina-reader.md): Converts any URL into LLM-friendly Markdown by prefixing it with https://r.jina.ai/. - [Linkup API](https://indexagentica.com/entries/linkup-api.md): Web search API for AI agents with search (standard or deep), page fetch and async deep research endpoints, plus a hosted MCP server. - [LurkAPI](https://indexagentica.com/entries/lurkapi.md): Social-media data API and remote MCP server: public posts, profiles, comments, transcripts and ad-library results from 16 platforms as JSON. - [MediaWiki Action API (Wikipedia)](https://indexagentica.com/entries/mediawiki-action-api.md): The MediaWiki Action API used by Wikipedia and other wikis to query and retrieve page content and metadata. - [OpenAI Realtime API](https://indexagentica.com/entries/openai-realtime-api.md): OpenAI's speech-to-speech API for low-latency voice agents over WebRTC, WebSocket or SIP, with tool calling, MCP servers, interruptions and handoffs. - [OpenAlex API](https://indexagentica.com/entries/openalex-api.md): Index of half a billion scholarly works with their authors, institutions, sources and topics, available via API and bulk download. - [OpenRouter](https://indexagentica.com/entries/openrouter.md): Unified API for hundreds of LLMs from many providers behind one endpoint and key, with model and price comparison. - [Orkas](https://indexagentica.com/entries/orkas-api.md): Metered chat, web search, speech, image and video APIs for external applications, alongside a local-first desktop AI team. - [Parallel Web APIs](https://indexagentica.com/entries/parallel-api.md): Web APIs for AI agents (Search, Extract, Task/Deep Research, FindAll, Monitor) for research, extraction and continuous monitoring. - [Perplexity API Platform](https://indexagentica.com/entries/perplexity-api.md): Perplexity's API platform with Agent, Search and Embeddings APIs for real-time, web-grounded research and Q&A. - [Rogue Agent Union](https://indexagentica.com/entries/rogue-agent-union.md): Public HTTPS forum where agents can read freely and, during a bounded trial, post via a temporary session without email or a profile. - [Semantic Scholar Academic Graph API](https://indexagentica.com/entries/semantic-scholar-api.md): API over Semantic Scholar's academic graph of papers, authors and citations; an API key unlocks some endpoints and higher rate limits. - [SerpApi](https://indexagentica.com/entries/serpapi.md): Real-time JSON API for structured search engine results from Google, Bing, Baidu and more; handles proxies and captchas. - [Tavily API](https://indexagentica.com/entries/tavily-api.md): Real-time web layer for AI agents: search, extract, crawl, map and cited research returned as clean LLM-ready content. - [Together AI](https://indexagentica.com/entries/together-ai.md): Hosted platform to run, train and serve open-source models via serverless inference, batch, dedicated and fine-tuning APIs. - [Vapi](https://indexagentica.com/entries/vapi.md): Hosted voice-agent API: build phone and web voice assistants that combine your chosen STT, LLM and TTS providers, with tools, MCP servers, telephony and testing. - [Wikidata Query Service](https://indexagentica.com/entries/wikidata-query-service.md): SPARQL endpoint for querying Wikidata's structured knowledge graph. - [Yumi Wheel Evidence](https://indexagentica.com/entries/yumi-wheel-evidence.md): Anonymous API that intersects wheel filename tags for 1-8 explicit PyPI releases with caller-supplied tags, returning PyPI-reported metadata. ## Information Knowledge sources, documentation hubs, datasets, benchmarks and research. JSON: https://indexagentica.com/api/information.json - [AgentBench](https://indexagentica.com/entries/agentbench.md): Comprehensive benchmark evaluating LLMs as agents (ICLR'24); the current repo is a function-calling version (AgentBench FC) with containerized tasks. - [AgentDojo](https://indexagentica.com/entries/agentdojo.md): ETH Zurich benchmark environment for prompt-injection attacks and defenses on tool-using LLM agents, with suites like workspace, banking, travel and slack. - [AgenticDataBench](https://indexagentica.com/entries/agenticdatabench.md): Benchmark for data-science agents: 344 tasks over 97 real datasets in 15 domains, with 433 fine-grained skill labels for skill-level scoring. - [Aider LLM Leaderboards](https://indexagentica.com/entries/aider-leaderboards.md): Quantitative benchmarks of LLM code-editing skill maintained by the Aider project. - [AndroidWorld](https://indexagentica.com/entries/android-world.md): Google Research environment and benchmark for autonomous Android control agents: 116 hand-crafted tasks across 20 apps on a live emulator. - [APIGen Function-Calling Dataset (xlam-function-calling-60k)](https://indexagentica.com/entries/xlam-function-calling-60k.md): Salesforce's 60,000-example function-calling dataset generated by APIGen, each example checked for format, by real execution and semantically. - [APIGen-MT-5k](https://indexagentica.com/entries/apigen-mt-5k.md): Salesforce dataset of 5,000 verified multi-turn agent trajectories (retail and airline, tau-bench style) for training and evaluating tool-calling agents. - [AppWorld](https://indexagentica.com/entries/appworld.md): Benchmark and sandbox of 9 simulated day-to-day apps operable via 457 APIs and populated by ~100 simulated people, for evaluating function-calling and interactive coding agents. - [Arena (formerly LMArena)](https://indexagentica.com/entries/arena-ai.md): Public, crowd-voted leaderboard comparing AI models on text, image and code through real-world head-to-head evaluation. - [Artificial Analysis](https://indexagentica.com/entries/artificial-analysis.md): Independent benchmarks comparing AI models and API providers on quality, price, output speed and latency. - [arXiv cs.AI (Artificial Intelligence)](https://indexagentica.com/entries/arxiv-cs-ai.md): arXiv's listing of the latest preprints in Artificial Intelligence, a primary source for new agent research. - [Berkeley Function Calling Leaderboard (BFCL)](https://indexagentica.com/entries/bfcl.md): UC Berkeley leaderboard evaluating how accurately LLMs call functions and tools; part of the Gorilla project. - [BigCodeBench](https://indexagentica.com/entries/bigcodebench.md): Code-generation benchmark with 1,140 software-engineering-oriented Python tasks that exercise diverse library calls, plus a harder task subset. - [BrowseComp](https://indexagentica.com/entries/browsecomp.md): OpenAI's benchmark of 1,266 hard-to-find, short-answer questions that test how persistently and creatively browsing agents search the web. - [BrowserGym](https://indexagentica.com/entries/browsergym.md): ServiceNow's Gym environment for web agents that bundles MiniWoB, WebArena, VisualWebArena, WorkArena, AssistantBench and more behind one API. - [BrowseSafe++](https://indexagentica.com/entries/browsesafe-plus-plus.md): Perplexity benchmark and SDK for detecting indirect prompt injection in web pages: 38,675 attack/control page pairs in 80 languages, with a leaderboard and adaptive attacks. - [Building Effective AI Agents (Anthropic)](https://indexagentica.com/entries/building-effective-agents.md): Anthropic engineering essay (Dec 19, 2024) on agent design patterns: workflows vs. agents, and when to use simple composable patterns. - [CLASHarness](https://indexagentica.com/entries/clasharness.md): Google Research benchmark and generator of 600 verifiable multi-agent conflict tasks in computer use: stale sub-agent reports, contradictory instructions, shared locks. - [Common Crawl](https://indexagentica.com/entries/common-crawl.md): Open repository of web crawl data that anyone can access and analyze. - [Epoch AI Benchmarking Hub](https://indexagentica.com/entries/epoch-ai-benchmarks.md): Epoch AI's hub of benchmark results for leading AI models, with trends over time by benchmark and by model. - [GAIA](https://indexagentica.com/entries/gaia-benchmark.md): Benchmark for general AI assistants ("Benchmarking General AI Agents"), published as a Hugging Face dataset under the gaia-benchmark org. - [GDPval](https://indexagentica.com/entries/gdpval.md): OpenAI benchmark of real-world, economically valuable knowledge-work tasks across 44 occupations; a 220-task gold subset with files and rubrics is open on Hugging Face. - [GPQA](https://indexagentica.com/entries/gpqa.md): Graduate-level 'Google-proof' multiple-choice Q&A benchmark; code is MIT, while the Hugging Face dataset is CC-BY-4.0 and gated. - [Hugging Face Daily Papers](https://indexagentica.com/entries/hf-daily-papers.md): Daily curated feed of new AI research papers on Hugging Face. - [Hugging Face Datasets Hub](https://indexagentica.com/entries/hf-datasets.md): Hugging Face hub of ready-to-use datasets for AI models, plus the open-source `datasets` library for loading and manipulating them. - [Humanity's Last Exam](https://indexagentica.com/entries/humanitys-last-exam.md): Multi-modal benchmark of 2,500 expert-written questions at the frontier of human knowledge, from the Center for AI Safety and Scale AI. - [InjecAgent](https://indexagentica.com/entries/injecagent.md): Benchmark of 1,054 test cases measuring how tool-using LLM agents fall for indirect prompt injections in tool outputs. - [LiveCodeBench](https://indexagentica.com/entries/livecodebench.md): Holistic, contamination-free evaluation of LLMs for code, with a public leaderboard. - [MCP-Bench](https://indexagentica.com/entries/mcp-bench.md): Accenture's benchmark for tool-using agents on complex real-world tasks across 28 live MCP servers and 250 tools (finance, travel, science, academic search). - [MCP-Universe](https://indexagentica.com/entries/mcp-universe.md): Salesforce AI Research benchmark and framework that evaluates LLMs and agents on real-world tasks against live MCP servers, with a public leaderboard. - [MCPMark](https://indexagentica.com/entries/mcpmark.md): Stress-testing benchmark for agentic models using real MCP environments (Notion, GitHub, Filesystem, Postgres, Playwright), with strict automated verifiers and sandboxed tasks. - [METR Task-Completion Time Horizons](https://indexagentica.com/entries/metr-time-horizons.md): METR's up-to-date measurements of how long tasks frontier AI models can complete autonomously (time horizons). - [Mind2Web](https://indexagentica.com/entries/mind2web.md): Dataset and benchmark for generalist web agents: 2,000+ open-ended tasks on 137 real websites across 31 domains, with crowdsourced action sequences (NeurIPS 2023). - [MLE-bench](https://indexagentica.com/entries/mle-bench.md): OpenAI benchmark measuring how well AI agents perform machine learning engineering tasks. - [Models.dev](https://indexagentica.com/entries/models-dev.md): Open-source database of AI model specifications, pricing and features, also served as JSON. - [Multi-SWE-bench](https://indexagentica.com/entries/multi-swe-bench.md): ByteDance Seed's multilingual issue-resolving benchmark: 1,632 verified tasks across Java, TS, JS, Go, Rust, C and C++. - [Open-SWE-Traces](https://indexagentica.com/entries/open-swe-traces.md): NVIDIA dataset of software-engineering agent trajectories (OpenHands, SWE-agent, mini-swe-agent, Claude Code, OpenCode) for distilling SWE agents; CC BY 4.0. - [OpenRouter LLM Rankings](https://indexagentica.com/entries/openrouter-rankings.md): LLM leaderboard by real-world usage, ranked by tokens processed through the OpenRouter API. - [OSWorld](https://indexagentica.com/entries/osworld.md): NeurIPS 2024 benchmark of multimodal agents on open-ended tasks in real computer environments. - [SimpleQA](https://indexagentica.com/entries/simpleqa.md): OpenAI factuality short-form QA benchmark, with a reference implementation in the MIT simple-evals repository. - [SWE-bench](https://indexagentica.com/entries/swe-bench.md): Benchmark and leaderboards (Verified, Lite, Multimodal, Multilingual) testing whether LLM agents can resolve real-world GitHub issues. - [SWE-Bench Pro](https://indexagentica.com/entries/swe-bench-pro.md): Scale AI benchmark of long-horizon software-engineering tasks for AI agents, with an open dataset on Hugging Face and a public leaderboard. - [SWE-Gym](https://indexagentica.com/entries/swe-gym.md): Environment and dataset for training software-engineering agents and verifiers on real GitHub tasks (ICML 2025). - [SWE-rebench](https://indexagentica.com/entries/swe-rebench.md): Nebius's continuously refreshed, decontaminated SWE agent benchmark and dataset: 21,000+ validated GitHub issue-PR tasks plus a time-windowed leaderboard. - [SWE-smith](https://indexagentica.com/entries/swe-smith.md): Toolkit and datasets for scaling training data for software-engineering agents by synthesizing task instances from GitHub repos (NeurIPS 2025 D&B). - [TermGrade](https://indexagentica.com/entries/termgrade.md): 1,004 executable Linux terminal tasks with pytest verifiers and per-model pass rates, plus 36,144 graded agent trajectories, for training and evaluating agents. - [Terminal-Bench](https://indexagentica.com/entries/terminal-bench.md): Continuously maintained benchmark and leaderboard (Stanford, Laude Institute) measuring how well AI agents complete hard, end-to-end tasks in real terminal environments. - [TheAgentCompany](https://indexagentica.com/entries/the-agent-company.md): Benchmark of 175 professional tasks in a simulated software company (self-hosted GitLab, Plane, ownCloud, RocketChat) for agents that browse, code, run programs and talk to coworkers. - [Toolathlon (Tool Decathlon)](https://indexagentica.com/entries/toolathlon.md): Benchmark of 108 long-horizon agent tasks across 32 real applications and 604 tools (mostly MCP servers), each checked by a deterministic evaluation script. - [ToolBench (ToolLLM)](https://indexagentica.com/entries/toolbench.md): Large tool-use instruction dataset over 16,464 real RapidAPI REST APIs, with the ToolEval evaluator and ToolLLaMA models. - [VisualWebArena](https://indexagentica.com/entries/visualwebarena.md): MIT benchmark of 910 multimodal visual web tasks for agents, extending WebArena with visually grounded sites and evaluation scripts. - [WebArena](https://indexagentica.com/entries/webarena.md): A realistic web environment for building autonomous agents, with benchmark tasks used to evaluate web agents. - [WebShop](https://indexagentica.com/entries/webshop.md): Princeton simulated e-commerce environment and benchmark for grounded language agents shopping from text instructions. - [WebVoyager](https://indexagentica.com/entries/webvoyager.md): Multimodal end-to-end web agent research code and 643-task dataset across 15 real websites, with GPT-4V auto-eval protocol. - [Windows Agent Arena](https://indexagentica.com/entries/windows-agent-arena.md): Microsoft's scalable OS benchmark for multimodal agents that perform tasks inside a real Windows environment, parallelizable on Azure. - [WorkArena](https://indexagentica.com/entries/workarena.md): ServiceNow browser-task benchmark for knowledge-work agents, evaluated through BrowserGym, with an Apache-2.0 Python package. - [τ-bench (tau2-bench)](https://indexagentica.com/entries/tau-bench.md): Sierra's benchmark for tool-agent-user interaction (airline, retail, telecom), now in six languages and full-duplex voice with v2.0. ## Finance & Payments Payment rails, wallets, billing and financial infrastructure usable by agents. JSON: https://indexagentica.com/api/finance-payments.json - [A2A x402 Extension](https://indexagentica.com/entries/a2a-x402.md): Extension bringing x402 crypto payments to the Agent2Agent (A2A) protocol so agents can monetize services with on-chain payments. - [Agent Payments Protocol (AP2)](https://indexagentica.com/entries/agent-payments-protocol.md): Open protocol for AI agents to make payments on behalf of users securely, complementing A2A and MCP. - [Agent Vault](https://indexagentica.com/entries/agent-vault.md): Virtual agent cards and stored logins for AI agents: the agent fills checkout and sign-in forms with mock tokens and real values are substituted out of its view. - [Agentic Commerce Protocol (ACP)](https://indexagentica.com/entries/agentic-commerce-protocol.md): Open standard from OpenAI and Stripe for programmatic checkout flows between buyers, their AI agents and businesses. - [Alby Hub](https://indexagentica.com/entries/alby-hub.md): Self-custodial Bitcoin Lightning node and wallet that apps (including agents) can control over Nostr Wallet Connect (NWC). - [Alby JS SDK (@getalby/sdk)](https://indexagentica.com/entries/getalby-sdk.md): JavaScript SDK for zero-custody bitcoin Lightning payments via Nostr Wallet Connect or the Alby Wallet API. - [Alby Lightning Tools (@getalby/lightning-tools)](https://indexagentica.com/entries/getalby-lightning-tools.md): Collection of JavaScript building blocks for Bitcoin Lightning web apps, such as Lightning address and invoice handling. - [ATXP](https://indexagentica.com/entries/atxp.md): Agent Transaction Protocol: agents self-register for a USDC wallet, email and connection token, then pay per use for MCP tools and LLM inference. - [Breez SDK - Spark](https://indexagentica.com/entries/breez-spark-sdk.md): SDK for adding instant, non-custodial bitcoin and stablecoin payments to apps and services; free for developers. - [buy (Celo)](https://indexagentica.com/entries/celo-buy.md): Celo's marketplace and CLI/MCP tool that lets agents pay per request in USDC, USD₮ or USA₮ on Celo for 780+ priced compute, data, blockchain and browser services, with no accounts or API keys. - [Catena](https://indexagentica.com/entries/catena.md): Banking and governance platform for AI agents supporting payments, treasury and other financial services. - [Circle Agent Stack](https://indexagentica.com/entries/circle-agent-stack.md): Circle's agent-native tooling (Circle CLI, agent wallets, nanopayments) for agents to hold and move USDC, pay for x402 services and stay within compliance guardrails. - [Circle CCTP](https://indexagentica.com/entries/circle-cctp.md): Cross-Chain Transfer Protocol: permissionless cross-chain transfers of USDC, EURC and registered third-party tokens. - [Circle Gateway (Nanopayments)](https://indexagentica.com/entries/circle-gateway.md): Unified USDC balance across chains with instant cross-chain minting; Gateway Nanopayments enable gasless sub-cent USDC micropayments via x402. - [Circle Wallets](https://indexagentica.com/entries/circle-wallets.md): APIs and SDKs for developer-controlled, user-controlled and modular (smart contract) wallets across multiple blockchains. - [Coinbase Agentic Wallet](https://indexagentica.com/entries/coinbase-agentic-wallet.md): Wallet tooling that lets AI agents hold, spend, trade and earn stablecoins with guardrails, via the awal CLI + skills or an MCP server. - [Coinbase AgentKit](https://indexagentica.com/entries/coinbase-agentkit.md): Coinbase Developer Platform's framework- and wallet-agnostic toolkit for giving AI agents a crypto wallet and onchain actions (Node.js and Python). - [Coinbase CDP Non-Custodial Wallets](https://indexagentica.com/entries/coinbase-cdp-wallets.md): Coinbase Developer Platform wallets for users (social login, no seed phrases) and for systems and agents (API key, keys held in a TEE). - [Coinbase CDP x402 Facilitator](https://indexagentica.com/entries/cdp-x402.md): Coinbase Developer Platform's x402 offering: a hosted facilitator that verifies and settles x402 payments, plus seller and buyer SDK quickstarts. - [Crossmint Agent Payments](https://indexagentica.com/entries/crossmint-agents.md): Crossmint's payment infrastructure for AI agents: scoped agent cards, agent wallets and agent checkouts across many blockchains. - [Kite Agent Passport](https://indexagentica.com/entries/kite-agent-passport.md): Agentic payment infrastructure giving AI agents identity, a funded wallet, delegated spending rules and onchain settlement with verifiable receipts. - [L402 (Lightning HTTP 402)](https://indexagentica.com/entries/l402.md): Lightning Labs standard for paying for and authenticating to APIs with Bitcoin Lightning payments; Aperture is the reference reverse proxy. - [Lightning Agent Tools](https://indexagentica.com/entries/lightning-agent-tools.md): Lightning Labs toolkit of seven composable skills plus an MCP server letting agents run a Lightning node, pay for L402 APIs and host paid endpoints. - [LNbits](https://indexagentica.com/entries/lnbits.md): Free, open-source Lightning wallet and accounts system for creating separate wallets and API keys on top of a funding source. - [LNbits NWC Service Provider](https://indexagentica.com/entries/lnbits-nwcprovider.md): LNbits extension that exposes LNbits wallets over Nostr Wallet Connect (NWC), using a Nostr relay. - [Machine Payments Protocol (MPP)](https://indexagentica.com/entries/machine-payments-protocol.md): Open standard for machine-to-machine payments over HTTP 402, co-developed by Tempo and Stripe; charge per API request, tool call or content. - [Mastercard Agent Pay for Machines (AP4M)](https://indexagentica.com/entries/mastercard-agent-pay-for-machines.md): Mastercard's x402-based machine-to-machine payments for AI agents: signed payment vouchers within pre-authorized budgets; early-access pilot, not commercially available. - [Mastercard Agent Suite for Merchants](https://indexagentica.com/entries/mastercard-agent-suite.md): Mastercard developer product to bring agentic commerce to merchants through a single integration. - [MetaMask Smart Accounts Kit](https://indexagentica.com/entries/metamask-smart-accounts-kit.md): MetaMask toolkit for smart contract accounts built on the open-source Delegation Framework contracts, supporting delegated execution on an account's behalf. - [Natural](https://indexagentica.com/entries/natural.md): Agentic payments platform: FDIC-insured wallets agents can hold and send from, plus ACH, wire and real-time payments, over API, MCP, CLI and SDKs. - [Nevermined](https://indexagentica.com/entries/nevermined.md): Payments infrastructure for AI agents: delegated spending, usage metering, payment plans and settlement across MCP, x402 and A2A. - [Nostr Wallet Connect (NWC)](https://indexagentica.com/entries/nostr-wallet-connect.md): Open protocol (Nostr NIP-47, draft) that lets clients and apps access a remote Bitcoin Lightning wallet in a standardized way. - [Paddle MCP Server](https://indexagentica.com/entries/paddle-mcp.md): Paddle's official MCP server for Paddle Billing: manage products, prices, customers, subscriptions, transactions, refunds and reports. - [pay.sh](https://indexagentica.com/entries/pay-sh.md): Single-binary CLI that transparently handles HTTP 402 (x402 and MPP) payments so agents can call paid APIs with no sign-up. - [PayAI x402 Facilitator](https://indexagentica.com/entries/payai-facilitator.md): x402 payment facilitator for AI agents and apps: accept stablecoin payments across supported Solana and EVM networks with one integration. - [PayPal Agent Toolkit and MCP Server](https://indexagentica.com/entries/paypal-agent-toolkit.md): PayPal toolkit (TypeScript) exposing PayPal APIs such as invoicing to OpenAI Agents SDK, LangChain, Vercel AI SDK and MCP, plus a hosted remote MCP server. - [Plaid Dashboard MCP](https://indexagentica.com/entries/plaid-mcp.md): Plaid's hosted MCP server with Production diagnostics: debug Items, review Link conversion and check usage metrics. - [Privy Agentic Wallets](https://indexagentica.com/entries/privy-agentic-wallets.md): Privy server wallets for agents and autonomous systems that execute onchain transactions independently under strict policy controls. - [Shopify Agentic Commerce](https://indexagentica.com/entries/shopify-agentic-commerce.md): Shopify developer platform for AI agents that authenticate with Shopify, search the Catalog, build carts and checkouts, and monitor orders via UCP. - [Skyfire](https://indexagentica.com/entries/skyfire.md): Identity and payments layer for AI agents: verified agent identity plus token-based payment credentials and stablecoin payments. - [Stripe Agentic Commerce](https://indexagentica.com/entries/stripe-agentic-commerce.md): Stripe integrations for selling through agents and embedding commerce in AI interfaces, including Shared Payment Tokens for agent-initiated purchases. - [Stripe for Agents (Stripe AI)](https://indexagentica.com/entries/stripe-agents.md): Stripe's agent toolkit: plugins, remote MCP, agent skills and SDKs for usage-based billing, agentic commerce and machine payments. - [Stripe Issuing for Agents](https://indexagentica.com/entries/stripe-issuing-for-agents.md): Issue cards and credentials that agents can use to purchase autonomously, with spend controls, real-time authorization decisioning and full visibility. - [Stripe Link CLI](https://indexagentica.com/entries/stripe-link-cli.md): Lets agents get one-time-use payment credentials from a Link wallet (virtual card, Link Pay Token or MPP Shared Payment Token) with user approval. - [Tempo](https://indexagentica.com/entries/tempo.md): Payments-first Layer 1 blockchain incubated by Stripe and Paradigm, purpose-built for stablecoin payments at scale; co-developer of MPP. - [Turnkey](https://indexagentica.com/entries/turnkey.md): Wallet and private-key infrastructure with policy-scoped signing, used for embedded wallets, server-side automation and AI agent wallets. - [Universal Commerce Protocol (UCP)](https://indexagentica.com/entries/universal-commerce-protocol.md): Open standard giving platforms (AI agents, apps), businesses, payment service providers and credential providers a common language for commerce. - [USDC](https://indexagentica.com/entries/usdc.md): Fully reserved dollar stablecoin issued by Circle, the settlement asset used by many agent payment rails including x402. - [Visa Intelligent Commerce](https://indexagentica.com/entries/visa-intelligent-commerce.md): Visa's portfolio for agentic commerce, embedding payment credentials, controls, authentication and protections into AI-initiated purchases. - [Visa Trusted Agent Protocol](https://indexagentica.com/entries/visa-trusted-agent-protocol.md): Signature-based framework (Oct 2025) letting merchants verify trusted commerce agents, distinguish them from malicious bots and receive consumer and payment context. - [Wavelength (Lightning Labs)](https://indexagentica.com/entries/wavelength.md): Lightning Labs' self-custodial Bitcoin wallet toolkit (Ark, Lightning swaps, on-chain) with an MCP server and L402 so agents can pay and get paid per request. - [x402 Bazaar](https://indexagentica.com/entries/x402-bazaar.md): Public catalog of x402 payment-gated services discovered by the CDP Facilitator; search by intent, browse resources or look up by merchant address. ## Directories Other directories, registries, awesome-lists and link hubs for the agent ecosystem. JSON: https://indexagentica.com/api/directories.json - [Awesome Agents (kyrolabs)](https://indexagentica.com/entries/awesome-agents-kyrolabs.md): Awesome list of AI agents and agent frameworks on GitHub. - [Awesome AI Agents (E2B)](https://indexagentica.com/entries/awesome-ai-agents.md): E2B's curated GitHub list of autonomous AI agents, open-source and closed-source. - [Awesome Claude Skills (Composio)](https://indexagentica.com/entries/awesome-claude-skills.md): Curated GitHub list of Claude Skills, resources and tools for customizing Claude workflows. - [Awesome Claude Skills (travisvn)](https://indexagentica.com/entries/awesome-claude-skills-travisvn.md): Curated list of Claude Skills, resources and tools for customizing Claude workflows, particularly Claude Code. - [Awesome GitHub Copilot](https://indexagentica.com/entries/awesome-copilot.md): GitHub's community collection of instructions, agents, skills and configurations for GitHub Copilot. - [Awesome LLM Apps](https://indexagentica.com/entries/awesome-llm-apps.md): Collection of 100+ free, open-source AI agents, agent skills and RAG apps with runnable code. - [Awesome MCP Servers (punkpeye)](https://indexagentica.com/entries/awesome-mcp-servers.md): Popular community-curated GitHub list of MCP servers, mirrored on Glama. - [Claude Code Plugins Directory (official)](https://indexagentica.com/entries/claude-plugins-official.md): Anthropic-managed directory of Claude Code plugins, with internal Anthropic plugins and vetted third-party plugins. - [ClawHub](https://indexagentica.com/entries/clawhub.md): Public registry for OpenClaw skills (SKILL.md bundles) and plugins, with versioning, vector search, moderation and a CLI for publishing. - [Docker MCP Catalog](https://indexagentica.com/entries/docker-mcp-catalog.md): Docker Hub's catalog of containerized, ready-to-use MCP servers, backed by the open docker/mcp-registry repo. - [GitHub MCP Registry](https://indexagentica.com/entries/github-mcp-registry.md): GitHub's registry centralizing MCP servers for discovery and integration with GitHub Copilot and other tools. - [Glama MCP Directory](https://indexagentica.com/entries/glama-mcp.md): Large directory of MCP servers, clients and remote connectors, each scanned, scored and testable in the browser, with a public API. - [HOL Plugins](https://indexagentica.com/entries/hol-plugins.md): HOL's searchable registry of agent plugins for Codex, Claude Code, Cursor, OpenCode, Copilot CLI and other runtimes, each with a 0-100 static-scan Trust Score. - [llms.txt Directory](https://indexagentica.com/entries/llmstxt-directory.md): Directory of websites that publish an llms.txt file, for finding LLM-friendly documentation entry points. - [llmstxt.site](https://indexagentica.com/entries/llmstxt-site.md): Directory of llms.txt files from products and services, following the llmstxt.org standard. - [MCP.so](https://indexagentica.com/entries/mcp-so.md): MCP marketplace for discovering MCP servers and clients. - [mcpservers.org (Awesome MCP Servers)](https://indexagentica.com/entries/mcpservers-org.md): Curated directory of 9,800+ official and community MCP servers with setup guides, backed by the wong2/awesome-mcp-servers list. - [Official MCP Registry](https://indexagentica.com/entries/official-mcp-registry.md): Community-driven registry service from the MCP project listing published MCP servers, with a public REST API (like an app store for MCP servers). - [OpenAI Plugins (Codex)](https://indexagentica.com/entries/openai-plugins.md): OpenAI's repository of plugins (skills and integrations) for Codex and ChatGPT surfaces; successor to openai/skills. - [Pipedream MCP](https://indexagentica.com/entries/pipedream-mcp.md): Pipedream's hosted MCP servers for more than 3,000 APIs with 10,000 prebuilt tools. - [PulseMCP](https://indexagentica.com/entries/pulsemcp.md): Site for browsing and discovering MCP servers, clients, use cases and news. - [skills.sh](https://indexagentica.com/entries/skills-sh.md): The open Agent Skills directory: browse skills ranked by installs and install them into your agent with one command. - [Smithery](https://indexagentica.com/entries/smithery.md): Public (non-proxied) MCP registry and directory of MCP servers, powered by Arcade.dev since Smithery's MCP Proxy and managed identity shut down on October 31, 2026. - [x402scan](https://indexagentica.com/entries/x402scan.md): Ecosystem explorer for x402: browse x402 servers, see their transaction volumes and access their resources through an embedded wallet. ## Infrastructure Hosting, sandboxes and runtimes that agents run on or execute code in. JSON: https://indexagentica.com/api/infrastructure.json - [1MCP](https://indexagentica.com/entries/1mcp.md): MCP runtime that aggregates many MCP servers behind `1mcp serve`, plus a CLI mode where agents discover tools progressively via instructions, inspect and run. - [Agent Sandbox (Kubernetes SIG Apps)](https://indexagentica.com/entries/kubernetes-agent-sandbox.md): Kubernetes CRD and controller for isolated, stateful, singleton sandbox pods for agent runtimes and RL, with templates, claims and warm pools. - [agentgateway](https://indexagentica.com/entries/agentgateway.md): Open-source Linux Foundation proxy for MCP and A2A that adds security, observability and governance to agent-to-LLM, agent-to-tool and agent-to-agent traffic. - [AIO Sandbox (agent-infra)](https://indexagentica.com/entries/aio-sandbox.md): All-in-one agent sandbox in a single Docker container: browser (VNC/CDP), shell, file system, VS Code Server, Jupyter and MCP sharing one file system. - [Amazon Bedrock AgentCore](https://indexagentica.com/entries/amazon-bedrock-agentcore.md): AWS agentic platform for building, deploying and operating agents securely at scale with any framework and foundation model. - [Anthropic Sandbox Runtime (srt)](https://indexagentica.com/entries/sandbox-runtime.md): Lightweight OS-level sandbox enforcing filesystem and network restrictions on agents, MCP servers and arbitrary processes, without a container. - [AReaL](https://indexagentica.com/entries/areal.md): Apache-2.0 fully asynchronous reinforcement-learning framework for large reasoning models, with a public Python package and docs. - [ART (Agent Reinforcement Trainer)](https://indexagentica.com/entries/openpipe-art.md): Open-source Python framework for training multi-step agents with GRPO, with an OpenAI-compatible client and a separate GPU training server. - [Blaxel](https://indexagentica.com/entries/blaxel.md): Infrastructure for autonomous agents: fast-resuming microVM sandboxes, agent hosting, MCP server hosting, batch jobs and a model gateway. - [Cloudflare AI Gateway](https://indexagentica.com/entries/cloudflare-ai-gateway.md): Cloudflare proxy for AI app traffic that adds analytics, logging, caching, rate limiting, request retries and model fallback with one line of code. - [Cloudflare Sandboxes](https://indexagentica.com/entries/cloudflare-sandbox.md): Execute untrusted or generated code on Cloudflare in Linux VMs (Containers) or isolated Dynamic Workers, via the Sandbox SDK. - [CodeRunner](https://indexagentica.com/entries/coderunner.md): Local sandbox for Mac that runs AI agents and their code in an isolated Apple container VM, exposed to clients as an MCP server. - [ContextForge (IBM MCP Context Forge)](https://indexagentica.com/entries/ibm-contextforge.md): IBM's open-source registry and proxy that federates MCP, A2A and REST/gRPC APIs into one endpoint with centralized governance, discovery, guardrails and observability. - [Cua](https://indexagentica.com/entries/cua.md): Open-source computer-use platform: full desktops for agents (Cua Spaces), a desktop-automation driver with MCP, local macOS/Linux VMs (Lume) and Cua Bench. - [Daytona](https://indexagentica.com/entries/daytona.md): Secure and elastic infrastructure (sandboxes) for running AI-generated code. - [Docker Sandboxes](https://indexagentica.com/entries/docker-sandboxes.md): Docker's `sbx` CLI runs coding agents like Claude Code and Codex in isolated microVM sandboxes, locally for free or on metered Docker-managed cloud compute. - [E2B](https://indexagentica.com/entries/e2b.md): Open-source, secure cloud sandboxes for AI agents: an isolated machine per agent to run code, browse and use tools. - [E2B Desktop Sandbox](https://indexagentica.com/entries/e2b-desktop.md): Open-source, isolated virtual Linux desktops for computer-use agents, built on E2B sandboxes, with Python and JavaScript SDKs and desktop streaming. - [Firecracker](https://indexagentica.com/entries/firecracker.md): AWS's open-source virtual machine monitor for secure, fast-booting microVMs; the isolation layer under many agent code sandboxes. - [Fly.io](https://indexagentica.com/entries/fly-io.md): Global public cloud with hardware-isolated Fly Machines for running full-stack and AI applications, driven by the flyctl CLI. - [Fly.io Sprites](https://indexagentica.com/entries/fly-sprites.md): Persistent, hardware-isolated Linux microVMs for running arbitrary code such as AI agents, with checkpoint/restore and per-second billing. - [Freestyle](https://indexagentica.com/entries/freestyle.md): Full Linux VMs for agents running untrusted code, built for long-running, complex tasks. - [GKE Sandbox (gVisor and microVM)](https://indexagentica.com/entries/gke-sandbox.md): Google Kubernetes Engine's sandboxed Pods for untrusted and agent-generated code: gVisor, or (GA since 2026-10-07) Kata Containers microVMs on Cloud Hypervisor. - [gVisor](https://indexagentica.com/entries/gvisor.md): Google's application kernel for containers that intercepts syscalls in user space, giving untrusted (e.g. agent-generated) code a stronger sandbox. - [Judge0](https://indexagentica.com/entries/judge0.md): Open-source sandboxed code execution system for 90+ languages; self-host or use Judge0 Cloud (via Rapid or direct). - [Kong AI Gateway](https://indexagentica.com/entries/kong-ai-gateway.md): Kong's AI gateway, managed through Konnect, applies AI policies to LLM traffic. Its AI MCP Proxy plugin turns APIs into MCP servers and proxies MCP traffic. - [LiteLLM MCP Gateway](https://indexagentica.com/entries/litellm-mcp-gateway.md): The LiteLLM Proxy's MCP Gateway gives one fixed endpoint for MCP tools, controls access by key and team, and lets any LiteLLM-supported model call them. - [Lizard Sandboxes](https://indexagentica.com/entries/lizard-sandboxes.md): Cloud Firecracker microVMs for AI agents, with code execution, a browser and desktop, snapshots, and Persistent Volumes. - [LLM Sandbox](https://indexagentica.com/entries/llm-sandbox.md): Python library and MCP server for running LLM-generated code in isolated backends (Docker, Kubernetes, Podman, Bubblewrap, NsJail, Windows) behind one API. - [MCPJungle](https://indexagentica.com/entries/mcpjungle.md): Self-hosted MCP gateway: register MCP servers once and expose them to Claude, Cursor, Codex or custom agents through a single endpoint, with tool groups and access control. - [MetaMCP](https://indexagentica.com/entries/metamcp.md): Docker-packaged MCP proxy that aggregates MCP servers into namespaces exposed as one MCP endpoint, with middleware, tool overrides and an inspector. - [microsandbox](https://indexagentica.com/entries/microsandbox.md): Easy, fast, programmable, local-first microVM runtime for untrusted workloads. - [Microsoft Foundry Agent Service](https://indexagentica.com/entries/microsoft-foundry-agent-service.md): Azure service for building and running AI agents with managed tools and runtime features in Microsoft Foundry. - [Microsoft MCP Gateway](https://indexagentica.com/entries/microsoft-mcp-gateway.md): Reverse proxy and management layer for MCP servers on Kubernetes, with stateless request routing, authorization, lifecycle management and a tool gateway router. - [Modal](https://indexagentica.com/entries/modal.md): Cloud platform for production AI: inference, training, sandboxes and serverless functions on one platform. - [Nango](https://indexagentica.com/entries/nango.md): Integration layer that gives agents and products auth, tool-calling actions, syncs and webhooks across 1,000+ APIs, including MCP auth and a management MCP. - [NeMo Gym](https://indexagentica.com/entries/nemo-gym.md): NVIDIA Apache-2.0 library for building, evaluating and scaling agent environments, verifiers and harnesses, including sandboxed code-execution tasks. - [NeMo RL](https://indexagentica.com/entries/nemo-rl.md): NVIDIA Apache-2.0 post-training / reinforcement-learning library for large-scale model training, with official docs and NGC containers. - [Northflank Sandboxes](https://indexagentica.com/entries/northflank-sandboxes.md): Secure microVM sandboxes for running untrusted, multi-tenant code at scale, in Northflank's cloud or your VPC. - [OpenAgentCore](https://indexagentica.com/entries/openagentcore.md): MiniMax's open-source, self-hosted implementation of OpenAI's Agents API that runs Codex, Claude Code or MiniMax Code sessions in sandboxes. - [OpenEnv](https://indexagentica.com/entries/openenv.md): BSD-3-Clause framework for building and serving isolated agentic RL environments over a Gymnasium-style reset/step/state API. - [OpenSandbox](https://indexagentica.com/entries/opensandbox.md): Open-source sandbox platform for running agents on your own infrastructure: isolated environments for code, commands, files, browsers and desktops, from Docker to Kubernetes. - [Piston](https://indexagentica.com/entries/piston.md): Self-hostable, high-performance engine for running untrusted code in many languages via a simple REST API. - [Portkey AI Gateway](https://indexagentica.com/entries/portkey-ai-gateway.md): AI gateway that routes to many LLMs behind one API with guardrails. Its MCP Gateway centralizes auth, access control and logging for MCP servers. - [prime-rl](https://indexagentica.com/entries/prime-rl.md): Prime Intellect’s Apache-2.0 asynchronous RL training framework, installed from git/uv (no verified PyPI package) and integrated with verifiers environments. - [rLLM](https://indexagentica.com/entries/rllm.md): Reinforcement-learning framework that reuses agent harnesses for evaluation and training, collecting rollouts and rewards across sandbox backends. - [Runloop](https://indexagentica.com/entries/runloop.md): Managed isolated Linux sandboxes (Devboxes) for AI coding agents, plus evaluations and production infrastructure. - [SandBase](https://indexagentica.com/entries/sandbase.md): Hosted one-key API for models, data APIs, agent sandboxes and MCP, with pay-per-call billing and a free catalog/discovery surface. - [SkyRL](https://indexagentica.com/entries/skyrl.md): Modular reinforcement-learning stack with a training engine, long-horizon agent layer and Gymnasium-style tool-use environments for LLMs. - [SPACE (Perplexity)](https://indexagentica.com/entries/perplexity-space.md): Perplexity's open-sourced sandbox platform: Firecracker microVM sandboxes behind an HTTP API, with templates, pause/suspend, warm pools and an E2B compatibility wrapper. - [Strands Box](https://indexagentica.com/entries/strands-box.md): Open-source local agent sandbox from AWS's Strands team: OS isolation plus default-deny Dogwood policies over shell, Python, network and MCP calls, with credential injection. - [SWE-ReX](https://indexagentica.com/entries/swe-rex.md): Runtime interface for coding agents to interact with persistent shell sessions across local and remote sandbox environments. - [Together Code Sandbox](https://indexagentica.com/entries/together-code-sandbox.md): Together AI's isolated runtime environments built from Docker-image snapshots for running commands and code, via the together-sandbox SDK and CLI. - [ToolHive](https://indexagentica.com/entries/toolhive.md): Stacklok's open-source platform that runs each MCP server in an isolated container with per-request identity and access policy and observability. - [Vercel AI Gateway](https://indexagentica.com/entries/vercel-ai-gateway.md): Managed Vercel gateway for calling AI models from any infrastructure, with centralized credentials, request logs, spend budgets, routing and provider failover. - [Vercel Sandbox](https://indexagentica.com/entries/vercel-sandbox.md): Ephemeral compute primitive that runs untrusted or agent-generated code in isolated Linux microVMs. - [verl](https://indexagentica.com/entries/verl.md): Distributed reinforcement-learning training library for LLMs, with GRPO/PPO dataflows and pluggable training and rollout engines for agentic post-training. ## Evals & Observability Evaluation, tracing and observability for agents and LLM applications. JSON: https://indexagentica.com/api/evals-observability.json - [AgentEnv Framework](https://indexagentica.com/entries/agentenv-framework.md): Scale AI's open-source Python SDK and CLI for building, deploying and scoring containerized agent environments and tasks for RL and evals. - [AgentEvals](https://indexagentica.com/entries/agentevals.md): LangChain's evaluators and utilities for agents, focused on agent trajectories (the intermediate steps an agent takes). - [AgentGym](https://indexagentica.com/entries/agentgym.md): Agent training and evaluation suite exposing diverse interactive environments through a common HTTP interface and Python clients. - [AgentOps](https://indexagentica.com/entries/agentops.md): Python SDK and platform for AI agent monitoring, LLM cost tracking, benchmarking, testing and debugging. - [Arize AX](https://indexagentica.com/entries/arize-ax.md): Arize's commercial platform for agent observability, evaluation, tracing and experimentation, from a free tier to self-hosted. - [Arize Phoenix](https://indexagentica.com/entries/arize-phoenix.md): Open-source AI observability and evaluation platform from Arize. - [Braintrust](https://indexagentica.com/entries/braintrust.md): AI observability platform for agents: trace production, run evals and catch regressions before users see them. - [CyberSecEval](https://indexagentica.com/entries/cyberseceval.md): Meta's benchmark suite for LLM cybersecurity risk and defensive skill: attack compliance, insecure code, prompt injection and SOC tasks. - [DeepEval](https://indexagentica.com/entries/deepeval.md): Open-source LLM evaluation framework with 50+ plug-and-play metrics for agents, RAG and chatbots. - [DeepTeam](https://indexagentica.com/entries/deepteam.md): Open-source framework from Confident AI to red team LLMs and AI agents. - [EvalPlus](https://indexagentica.com/entries/evalplus.md): Code-generation evaluation framework with expanded HumanEval+/MBPP+ tests and EvalPerf for checking correctness and runtime efficiency. - [Evidently](https://indexagentica.com/entries/evidently.md): Open-source Python framework to evaluate, test and monitor ML and LLM systems, with 100+ built-in metrics, LLM judges, test suites for CI and a monitoring UI. - [garak](https://indexagentica.com/entries/garak.md): NVIDIA's open-source LLM vulnerability scanner probing for hallucination, data leakage, prompt injection, jailbreaks, toxicity and other weaknesses. - [Giskard](https://indexagentica.com/entries/giskard.md): Open-source Python library for testing agentic systems: scenario-based checks and LLM-as-judge evals (giskard-checks) plus a vulnerability scanner for red teaming (giskard-scan). - [Guardrails AI](https://indexagentica.com/entries/guardrails-ai.md): Open-source Python framework for adding input/output guardrails (validators) to LLM applications. - [Harbor](https://indexagentica.com/entries/harbor.md): Framework from the Terminal-Bench creators for evaluating and optimizing agents and models in sandboxed environments, run in parallel across cloud sandbox providers. - [Helicone](https://indexagentica.com/entries/helicone.md): Open-source AI gateway and LLM observability platform for routing, monitoring, evaluating and experimenting. - [Inspect](https://indexagentica.com/entries/inspect-ai.md): Open-source framework for large language model and agent evaluations from the UK AI Security Institute. - [Inspect Evals](https://indexagentica.com/entries/inspect-evals.md): Community collection of ready-to-run evaluation tasks for the UK AISI Inspect AI framework. - [Invariant Guardrails](https://indexagentica.com/entries/invariant-guardrails.md): Rule-based guardrails that sit between an agent and its MCP servers or LLM provider, checking and blocking tool calls and messages. - [Laminar](https://indexagentica.com/entries/laminar.md): Open-source observability platform purpose-built for AI agents: trace, evaluate and debug agent failures. - [Langfuse](https://indexagentica.com/entries/langfuse.md): Open-source agent evals and observability platform: trace, evaluate and improve LLM applications and agents. - [Langfuse Experiment Action](https://indexagentica.com/entries/langfuse-experiment-action.md): GitHub Action that runs a Langfuse experiment in your CI pipeline. - [LangSmith](https://indexagentica.com/entries/langsmith.md): LangChain's agent and LLM observability and evaluation platform: tracing, monitoring, cost and latency tracking. - [LangWatch](https://indexagentica.com/entries/langwatch.md): Open-core platform for agent observability and evals: tracing, agent simulation tests, evaluations, prompt management, an AI gateway and coding-agent usage tracking. - [Lighteval](https://indexagentica.com/entries/lighteval.md): Hugging Face toolkit for evaluating LLMs across local and served-model backends, with customizable tasks, metrics and per-sample results. - [Llama Guard](https://indexagentica.com/entries/llama-guard.md): Meta's open-weight safety classifiers that label LLM prompts and responses as safe or unsafe against the MLCommons hazard taxonomy. - [Llama Prompt Guard 2](https://indexagentica.com/entries/llama-prompt-guard-2.md): Meta's small open-weight classifiers (86M and 22M) that flag prompt injection and jailbreak attempts in user input and untrusted content. - [LlamaFirewall](https://indexagentica.com/entries/llamafirewall.md): Meta's open-source guardrail framework for agents that chains scanners for prompt injection, goal hijacking and insecure generated code. - [LM Evaluation Harness](https://indexagentica.com/entries/lm-evaluation-harness.md): EleutherAI's widely used framework for few-shot evaluation of language models across hundreds of benchmarks, with HF, vLLM and API backends. - [MCP Inspector](https://indexagentica.com/entries/mcp-inspector.md): Official interactive developer tool for testing and debugging MCP servers in the browser, on the command line or in the terminal. - [MLflow](https://indexagentica.com/entries/mlflow.md): Open-source AI engineering platform for agents, LLMs and ML models: OpenTelemetry-based tracing, evaluation with 50+ metrics and LLM judges, prompt registry and an AI Gateway. - [NeMo Guardrails](https://indexagentica.com/entries/nemo-guardrails.md): NVIDIA's open-source toolkit for adding programmable guardrails to LLM-based conversational systems. - [OmniMemEval](https://indexagentica.com/entries/omnimemeval.md): MemTensor's evaluation framework for memory backends (LoCoMo, LongMemEval, BEAM, PersonaMem v2, HaluMem) and memory-equipped agents on AgentBench domains. - [OpenAI Evals](https://indexagentica.com/entries/openai-evals.md): OpenAI's open-source framework and registry of benchmarks for evaluating LLMs and LLM systems, including custom private evals. - [OpenAI Frontier Evals](https://indexagentica.com/entries/openai-frontier-evals.md): OpenAI's open-source code for frontier capability evals: PaperBench, SWE-Lancer and EVMbench. - [OpenEvals](https://indexagentica.com/entries/openevals.md): LangChain's package of ready-made evaluators for LLM apps (sibling project agentevals targets agents). - [OpenInference](https://indexagentica.com/entries/openinference.md): OpenTelemetry-compatible conventions and auto-instrumentation packages for tracing LLM calls, retrieval, tools and agent frameworks. - [OpenLIT](https://indexagentica.com/entries/openlit.md): Open-source, OpenTelemetry-native platform for AI agents: tracing, evals, guardrails, prompt hub, vault, and cost and GPU monitoring; self-host free. - [OpenLLMetry](https://indexagentica.com/entries/openllmetry.md): Traceloop's open-source observability for GenAI/LLM applications, built on OpenTelemetry. - [Opik](https://indexagentica.com/entries/opik.md): Comet's open-source platform to debug, evaluate and monitor LLM apps, RAG systems and agentic workflows. - [Promptfoo](https://indexagentica.com/entries/promptfoo.md): Open-source tool to test and red-team prompts, agents and RAG: automated evals, vulnerability scanning and model comparison. - [Promptfoo GitHub Action](https://indexagentica.com/entries/promptfoo-action.md): GitHub Action for running Promptfoo prompt, agent and RAG tests and red-team scans in CI. - [Pydantic Logfire](https://indexagentica.com/entries/pydantic-logfire.md): OpenTelemetry-based observability platform from the Pydantic team for tracing LLM apps and agents, with SQL querying and evals. - [PyRIT](https://indexagentica.com/entries/pyrit.md): Microsoft's open-source Python Risk Identification Tool for proactively red teaming generative AI systems. - [Ragas](https://indexagentica.com/entries/ragas.md): Open-source evaluation toolkit for LLM apps and agents: LLM-based and traditional metrics for RAG and agent workflows, plus automatic test-set generation. - [Seahaven](https://indexagentica.com/entries/seahaven.md): Kiln AI's open-source Python framework for synthetic, resettable 'worlds' (SQLite state plus mock tools) for agent evals and RL, served via OpenEnv or MCP. - [Snyk Agent Scan](https://indexagentica.com/entries/snyk-agent-scan.md): Security scanner that discovers agent components on your machine (agents, MCP servers, skills) and scans them for prompt injections and vulnerabilities. - [ThinkingBox](https://indexagentica.com/entries/thinkingbox.md): Microsoft's open-source sandbox and benchmark that runs agents against isolated MCP tool servers and grades the backend state and side effects they leave. - [TruLens](https://indexagentica.com/entries/trulens.md): Open-source, OpenTelemetry-native tracing and evaluation for LLM apps and agents, scoring each step with LLM judges and comparing app versions. - [verifiers](https://indexagentica.com/entries/verifiers.md): Prime Intellect’s MIT library for creating LLM reinforcement-learning environments and evals, with a matching PyPI package. - [W&B Weave](https://indexagentica.com/entries/wandb-weave.md): Weights & Biases toolkit for tracking, testing and improving LLM-powered applications. ## Optional - [Contributing guide](https://github.com/Drudley/indexagentica/blob/main/CONTRIBUTING.md): PR-based submission process - [Sitemap](https://indexagentica.com/sitemap.xml)