Agent Docs MCP server

rag-context-assembly

Ask questions about Claude Code, Cursor, Codex and MCP — get answers grounded in their official docs, with citations.

A hybrid RAG service that AI agents call through two MCP tools (or over REST). It indexes ~600 pages of official documentation, refreshes itself daily, and every design choice is backed by an experiment.

Why it is built this way, what was tested, and a glossary of every term:

ARCHITECTURE.md

How it works

Your agent calls a remote MCP server with two tools: searchdocs, then readsection when a passage is not enough. No model runs on this path; the agent writes the answer itself.

Diagram source: docs/diagrams/readme-how-it-works.mmd

The /ask REST endpoint, for clients that are not agents, adds a few steps after the rerank:

searchdocs stops after the rerank and returns the best passage of each page, so one long page cannot fill the list. Each passage carries the page's one-line description. The agent reads the passages itself, which is cheaper; for a longer read, readsection returns a page's outline, then one section's text from the stored page (no model call). Every request is traced in Langfuse.

Fresh every day

Diagram source: docs/diagrams/readme-daily-refresh.mmd

New pages are indexed automatically; suspicious ones wait for a human. Each run writes a short report of what changed in the products: reports/docs-changes/.

What it covers

Connect

Two ways in, one header each:

dashboard.cohere.com. Reranking runs on your key; the key is used for that request only and never stored or logged. Limit: 30 requests/min per IP.

• Your own Cohere key: X-Cohere-Api-Key: . A free trial key is at

• A token from the owner: Authorization: Bearer .

Shortened. The full README is on GitHub.