Documentation: how ready are these sites for AI agents?
Reference and API documentation sites. Agents and RAG pipelines fetch these heavily, so readable structure, content negotiation, and a published rubric of sections matter most.
Share of measured documentation sites failing each check. The denominator is sites where the check actually ran — a check we skipped is never counted as a pass.
An API catalog is published at `/.well-known/api-catalog` (RFC 9727) or an OpenAPI document is reachable at `/openapi.json` or `/openapi.yaml`.
No MCP endpoint, so an agent cannot transact programmatically.
`/.well-known/oauth-authorization-server` is reachable and conforms to RFC 8414, letting agents discover authorization endpoints without out-of-band setup.
`/.well-known/oauth-protected-resource` is published per RFC 9728 so agents can discover required scopes and authorization servers programmatically.
The site signals support for the Web Bot Auth IETF draft (HTTP Message Signatures over a known JWKS) so well-behaved agents can prove identity.
No published agent skills, so an agent has no described path to purchase.
HTTP `Link:` response headers carry useful relations (canonical, alternate, describedby) that agents consume without parsing HTML.
Requests with `Accept: text/markdown` return a markdown representation of the page (Markdown content negotiation).
An MCP Server Card is reachable at `/.well-known/mcp/server-card.json` (or referenced from a Link header) and validates against the Model Context Protocol spec.
No structured data, so price and availability have to be guessed from prose.
Same rubric as every site above, against a published and versioned checklist. Free, about 30 seconds, and your score gets a permanent public URL.
Run a free check →Every figure here is a real measurement against our published rubric, recomputed as we re-scan. Sites that disallow AgentSpeedBot in robots.txt are excluded before we fetch them.