Docs MCP

The Docs MCP is the agent-native documentation surface from the builder test: the same corpus the site renders, exposed as three read-only tools. Public, stateless, no token.

Why public

The corpus is already public byte for byte, so the read-only server is ungated; the Procurement MCP mutates state and stays token-gated.

Connect it

https://partifact-docs-mcp.thanhvuttv.workers.dev/mcp

1. No token, no slot, just paste the URL. In claude.ai: Settings → Connectors → Add custom connector.

2. Once connected, sanity-check it: ask the agent to run search_docs("verify webhook signature"). It should return the Webhooks page.

Liveness (no token needed):

curl https://partifact-docs-mcp.thanhvuttv.workers.dev/

The 3 tools

Tool	Args	Returns
list_docs	none	Every page: { path, title, summary }. Read this first to plan which pages you need.
get_doc	path	One page as raw markdown (.md / docs/ prefix accepted). A miss returns an enriched error listing the available paths.
search_docs	query	Best-matching pages, ranked by term density, each with a snippet.

Each tool returns structuredContent plus a one-screen text summary (parity with the Procurement MCP).

When to use it vs. the docs site

They serve the same corpus through two channels. Pick by who is reading:

• A human, or an agent that can browse → the rendered docs portal, or /llms.txt / /llms-full.txt for a single-fetch dump.
• An agent mid-task that wants targeted retrieval → the Docs MCP. search_docs surfaces the right page without spending context on a crawl.