Reference
WebMCP Registry Reference
Inspect the public registry of WebMCP-capable sites that PurposeBot crawls, verifies, and publishes for agent ingestion.
PurposeBot continuously crawls the web for sites that publish a WebMCP discovery
document, verifies them, and publishes the
confirmed set as a public JSON registry at
/api/webmcp/registry.json. Agents
use it for bulk ingestion; this reference shows the same feed in a human-readable form.
Live WebMCP registry
Loading registry...
How it works
The explorer fetches the registry document directly from the production API — the same endpoint any agent would call. Each entry carries the site's domain, a confidence score from the verification pipeline, and a fingerprint of its discovery document so consumers can detect changes between crawls.
There is no authentication on this feed: it is intentionally public so that agent frameworks can discover WebMCP-capable sites without an account. For the richer search surface (trust scores, intent keywords, tool manifests), see the agent discovery quickstart and the marketplace search.