Docy

A Model Context Protocol server that provides documentation access capabilities. This server enables LLMs to search and retrieve content from documentation websites by scraping them with crawl4ai. Built with FastMCP v2.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "oborchers-mcp-server-docy": {
      "command": "uvx",
      "args": [
        "mcp-server-docy"
      ],
      "env": {
        "DOCY_DOCUMENTATION_URLS": "https://docs.crawl4ai.com/,https://react.dev/"
      }
    }
  }
}

Docy MCP Server gives you a self-hosted way to access and query documentation sources from your MCP-enabled tooling. It scrapes documentation sites, caches content for fast responses, and exposes an MCP endpoint you can connect to from Claude Code, VS Code, or other MCP-enabled assistants to pull in up-to-date docs on demand.

How to use

You connect your MCP client to the Docy server to search, fetch, and navigate documentation sources. Start by running the server with one of the available startup methods, then configure your client to point to the server’s endpoint. From there you can request full documentation pages, discover related links, or list all configured sources. This makes it easier to verify implementation details, compare usage patterns, and ensure you reference current guidance while coding.

How to install

Prerequisites you need before installation: Python or Node tooling depending on how you run the server. You will also need an MCP client setup to connect to the Docy server.

# Using uvx (recommended) to run the MCP server directly
uvx -M mcp-server-docy

# Using pip to install the package and start with an environment variable
pip install mcp-server-docy
DOCY_DOCUMENTATION_URLS="https://docs.crawl4ai.com/,https://react.dev/" python -m mcp_server_docy

# Using Docker to run the server with documentation URLs mounted
docker pull oborchers/mcp-server-docy:latest
docker run -i --rm -e DOCY_DOCUMENTATION_URLS="https://docs.crawl4ai.com/,https://react.dev/" oborchers/mcp-server-docy

Additional sections

Configuration, troubleshooting, and notes below cover how to set up environment variables, run modes, and how to connect from MCP clients. You’ll find exact commands for starting the server in the available startup options and the required environment variables to customize behavior.

Available tools

list_documentation_sources_tool

List all available documentation sources.

fetch_documentation_page

Fetch the content of a documentation page by URL as markdown.

fetch_document_links

Fetch all links from a documentation page.

Built by

VeilStrat

AI signals for GTM teams