# AgentFit API documentation

Audit any public API documentation site against a 30-criteria AI-readiness rubric over HTTP,
the CLI, or a remote MCP server. AgentFit returns a deterministic 0–100 report with concrete
HTTP evidence for every criterion, and makes no LLM calls at run time.

## Getting started

- [Documentation home](https://docs.agentfit.dev/)
- [OpenAPI specification](https://docs.agentfit.dev/openapi.yaml) — the machine-readable contract (OpenAPI 3.1)
- [Full text for LLMs](https://docs.agentfit.dev/llms-full.txt)

## Quickstart

```
curl -s -X POST 'https://agentfit.dev/audit?async=true' \
  -H 'Content-Type: application/json' \
  -d '{"base_url":"https://docs.stripe.com"}'
```

Poll `GET https://agentfit.dev/api/public/audit/RUN_ID` until `status` is `done`.

## MCP server

```
claude mcp add --transport http agentfit https://docs.agentfit.dev/mcp
```

Tools: `audit(base_url, format)` and `get_report(run_id)`, scope `agentfit:audit`.