LABSCO SUMMARY

You run the index, so you decide what is in it and where it lives.

The trade against a hosted documentation service is plain: more setup - a vector store, an embedding key, a Worker deploy - in exchange for owning the pipeline and the data. The reindex is a command you run, which means freshness is your responsibility rather than something that happens invisibly.

What it is

A scaffolding tool rather than a running service. It generates a project that parses your documentation, chunks and embeds it, stores it in Pinecone, and deploys a Cloudflare Worker that answers MCP and REST queries against it.

What you get

A project scaffolded by one command, with a config file listing the documentation sources to index
Three parsers: MDX and JSX documentation as produced by Mintlify, Fumadocs or Docusaurus; plain Markdown for READMEs and changelogs; and OpenAPI or Swagger specs for API reference
Chunking sized for search rather than for reading, and embeddings from OpenAI or Gemini
A search endpoint served from your own Cloudflare Worker, reachable over MCP or as REST
A companion chat widget that queries the same endpoint and streams answers with inline citations

Requirements

Node.js 18+. Scaffold with npx contextmcp init, then supply two keys in the .env: a Pinecone API key for the vector store, and an embedding provider key - OpenAI or Gemini depending on the provider you choose. List your documentation sources in config.yaml, run the reindex, then deploy the Cloudflare Worker. The licence is Apache 2.0.

Setup effort

One command plus a key — npx contextmcp init my-docs-mcp, then supply credentials

See installation options

USE CASES

01

Giving an assistant your product's real documentation

Point the config at the docs site source, index it, and let the assistant search that instead of whatever it remembers.

02

Making an API reference searchable

Add the OpenAPI spec as a source so endpoint documentation is chunked and retrievable alongside the prose.

03

Adding Ask AI to your docs site

Deploy the companion chat widget against the same search endpoint, so the site and the assistant answer from one index.

BEFORE YOU INSTALL

What to know first

Requires

npx on PATH
Node.js 18+
PINECONE_API_KEY in your environment

INSTALLATION

Connect your client

Add the block to your client, or run the command directly.

Server setup

Configuration file

JSON

{
  "mcpServers": {
    "contextmcp": {
      "command": "npx",
      "args": [
        "-y",
        "contextmcp"
      ]
    }
  }
}

The configuration on this page does not set PINECONE_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.

npx

TERMINAL

npx contextmcp init my-docs-mcp

ContextMCP