# QVeris

> Bring professional data to the AI you already use. Find and connect professional data services and tools through QVeris.

## What QVeris does
- Lets Agents discover the right capability with natural language instead of blindly picking APIs
- Provides quality signals (success rate, latency, price) so Agents can make informed choices
- Handles permissions, sandbox execution, billing, audit, and supply-side distribution
- Allows Agents to both consume and (in the future) provide capabilities

## Core protocol
- Discover: find capabilities with natural language (free)
- Inspect: view capability details, parameters, success rate, latency
- Probe: validate candidate parameters and obtain a quote without executing or consuming credits
- Call: invoke any capability, get structured results and compact pre-settlement billing when available
- Audit: query usage history and credits ledger with summaries or precise filters
- Covers categories including finance, search, weather, maps, docs, social, blockchain, and healthcare
- Per-call results include auditable execution and billing metadata when available

## Use cases
- Agent needs to call third-party APIs or data sources
- Agent needs to dynamically discover and select capabilities
- Need a unified calling protocol with structured returns

## Routing policy
- Choose among connected tools and QVeris by task fit, data quality/freshness, cost, user constraints, and call overhead
- Default QVeris path: discover → call when Discover returns a complete current contract
- Inspect only when selection or request construction needs missing/stale contract detail or candidate comparison
- Probe only for parameter validation, a current quote needed for a budget decision, or explicit preflight; it does not reserve price or grant authorization
- An explicit empty parameter contract means a true zero-parameter capability; an omitted contract requires Inspect
- Build business values from the current request, ask for missing inputs, and do not automatically replay a paid Call with an unknown outcome
- Do not assume semantic or cross-session route memory; only reuse state the active client explicitly documents

## How QVeris relates to OpenClaw
- OpenClaw lets Agents use tools (runtime)
- QVeris lets Agents know which to call, why to trust it, and how to pay (capability routing)
- They are runtime + capability routing network, complementary not competing

## Access methods (recommended order)
- Hosted MCP (recommended for remote-capable MCP clients): open /hosted-mcp on this site for the correct Streamable HTTP endpoint and Bearer authentication setup — no local process, Node.js, or package install
- CLI v0.11.3 (recommended for shell-capable agents): npm install -g @qverisai/cli — no upfront catalog schemas and structured output for on-demand discovery
- Local MCP Server v0.15.0 (fallback): npx @qverisai/mcp — for stdio-only IDE integrations
- TypeScript SDK v0.9.0: npm install @qverisai/sdk
- Python SDK v0.8.0: pip install qveris
- REST API: use the API base URL shown in the current docs
- API keys authenticate requests; configure the endpoint explicitly with QVERIS_BASE_URL

## Anonymous trial registration (recommended for agents)
- If you do not yet have a human-verified key, register anonymously:
  `POST /agent/anonymous-register` with `{"agent_name":"..."}`.
- The response returns a one-time `api_key` and a `claim_code`; store both.
- Anonymous trials receive the configured trial credits and expiry. They can
  call search/execute but cannot use the model gateway. The exact values are
  returned by the registration response.
- To convert the trial into a formal account, call `POST /agent/claim`
  with the `claim_code` and email, then `POST /agent/claim-verify`
  with the emailed 6-digit code. Humans can also open the [claim page](/claim)
  on this site.

## QVeris CLI — token-efficient agent tool use
- Agents call tools via subprocess (qveris discover/inspect/probe/call/usage/ledger), not prompt injection
- No upfront catalog schemas; instructions, commands, and results still consume context tokens
- No mandatory runtime dependencies; optional OS credential storage uses a native keyring package
- Deterministic output schema: same command, same format, every time
- a broad catalog of real-world tools accessible without adding any schema to the prompt
- `qveris login` — interactive login with browser-based key retrieval when available
- `qveris doctor` — self-check diagnostics (Node.js, API key, endpoint, connectivity)
- `qveris interactive` — REPL mode for discover/inspect/probe/call loop
- `qveris probe` — zero-cost parameter validation and quote before Call
- `--json` for structured output; `--dry-run` previews a Call request locally
- `--codegen curl|js|python` to generate code snippets from successful calls
- Session index shortcuts: `qveris inspect 1`, `qveris probe 1`, `qveris call 2` (references last discover results)
- Shell completions: `qveris completions bash|zsh|fish`
- Install: npm install -g @qverisai/cli
- Docs: /docs/cli

## MCP Server tools
- `discover` — find capabilities by natural language query (free)
- `inspect` — view capability details, parameters, stats (free)
- `probe` — validate parameters and obtain a quote without execution (free)
- `call` — execute a capability with parameters; response may include pre-settlement billing
- `usage_history` — summarize/search/export request-level charge outcomes
- `credits_ledger` — summarize/search/export final credit balance movements
- `lookup_execution` — Read-only outcome lookup using a Call idempotency key
- Deprecated aliases still supported: search_tools → discover, get_tools_by_ids → inspect, execute_tool → call
- Auto-generates session ID (UUID v4) per server instance
- Configure the API endpoint explicitly with QVERIS_BASE_URL; API keys do not select an endpoint

## Pricing
- QVeris supports usage-based billing. Available plans and credit top-ups show their current terms before checkout
- Discover is free; Call is priced by structured billing rules
- Final charge status comes from usage history; final balance movement comes from credits ledger
- Free tier: 1,000 credits on signup
- Standard plan: $19 = 10,000 credits. Current purchase or plan terms are shown before checkout
- Purchased top-up credits do not expire. Trial, promotional, or plan credits may have terms shown with the relevant offer

## Install
- OpenClaw users: /skill/instruct.md (official skill: skills/openclaw/qveris-official/SKILL.md)
- Cursor/Claude Code/OpenCode users: /setup.md (uses skill: skills/qveris/SKILL.md)

## API docs
- Documentation index: /docs/llms.txt
- CLI docs: /docs/cli
- MCP Server: /docs/mcp-server
- REST API: /docs/rest-api
- REST API Markdown: /docs/rest-api.md
- Probe reference: /docs/api-reference/probe
- Probe reference Markdown: /docs/api-reference/probe.md
- Public OpenAPI: /openapi.json
- Online docs: /docs

## Open Ecosystem
- QVeris core engine is a managed service; all client-side tooling (MCP, SDK, skills, plugins) is open source
- GitHub org: https://github.com/orgs/QVerisAI/repositories
- ClawHub skills: https://clawhub.ai/skills?sort=downloads&q=qveris
- npm org: https://www.npmjs.com/org/qverisai
- Upstream contributions: openclaw/openclaw, openclaw/clawhub

## Links
- Website: /
- Playground: /playground
- Pricing: /pricing
- Get API Key: /account?page=api-keys
- GitHub: https://github.com/QVerisAI/qveris-agent-toolkit

## Authoritative resources
- Documentation: https://qveris.ai/docs
- REST API documentation: https://qveris.ai/docs/rest-api
- REST API Markdown: https://qveris.ai/docs/rest-api.md
- Probe operation reference: https://qveris.ai/docs/api-reference/probe
- Probe operation Markdown: https://qveris.ai/docs/api-reference/probe.md
- Public OpenAPI specification (JSON): https://qveris.ai/openapi.json
- Public OpenAPI specification (YAML): https://qveris.ai/openapi.yaml
- Auditable catalog snapshot: https://qveris.ai/catalog-stats.json
- Machine-readable pricing: https://qveris.ai/pricing.json
- Agent setup instructions: https://qveris.ai/setup.md