Docy (Documentation Access) MCP server for AI agents

Docy is a Model Context Protocol (MCP) server that provides AI assistants with direct access to technical documentation. It allows AI tools to search and retrieve content from documentation websites in real-time, ensuring accuracy and eliminating issues like outdated information or rate limits.

Installation Options

Using uv (Recommended)

No specific installation is needed when using uv. Simply use uvx to run the server directly:

uvx mcp-server-docy

Using PIP

Install via pip:

pip install mcp-server-docy

Then run as a script:

DOCY_DOCUMENTATION_URLS="https://docs.crawl4ai.com/,https://react.dev/" python -m mcp_server_docy

Using Docker

Pull and run the Docker image:

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

Configuration

Configuring for Claude.app

Add to your Claude settings:

Using uvx:

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

Using Docker:

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

Using pip installation:

"mcpServers": {
  "docy": {
    "command": "python",
    "args": ["-m", "mcp_server_docy"],
    "env": {
      "DOCY_DOCUMENTATION_URLS": "https://docs.crawl4ai.com/,https://react.dev/"
    }
  }
}

Configuring for VS Code

Add to your User Settings (JSON) file or .vscode/mcp.json in your workspace:

Using uvx:

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

Using Docker:

{
  "mcp": {
    "servers": {
      "docy": {
        "command": "docker",
        "args": ["run", "-i", "--rm", "oborchers/mcp-server-docy:latest"],
        "env": {
          "DOCY_DOCUMENTATION_URLS": "https://docs.crawl4ai.com/,https://react.dev/"
        }
      }
    }
  }
}

Configuration Options

Configure using environment variables:

DOCY_DOCUMENTATION_URLS: Comma-separated list of documentation URLs
DOCY_DOCUMENTATION_URLS_FILE: Path to file with URLs (default: ".docy.urls")
DOCY_CACHE_TTL: Cache time-to-live in seconds (default: 432000)
DOCY_CACHE_DIRECTORY: Path to cache directory (default: ".docy.cache")
DOCY_USER_AGENT: Custom User-Agent for HTTP requests
DOCY_DEBUG: Enable debug logging ("true", "1", "yes", or "y")
DOCY_SKIP_CRAWL4AI_SETUP: Skip crawl4ai-setup at startup
DOCY_TRANSPORT: Transport protocol ("sse" or "stdio", default: "stdio")
DOCY_HOST: Host address to bind to (default: "127.0.0.1")
DOCY_PORT: Port number (default: 8000)

URL Configuration File

Instead of environment variables, create a .docy.urls file with one URL per line:

https://docs.crawl4ai.com/
https://react.dev/
# Lines starting with # are comments
https://docs.python.org/3/

This file supports hot-reload, allowing you to add or modify URLs without restarting the server.

Using Docy

Available Tools

list_documentation_sources_tool: Lists all available documentation sources
- No parameters required
fetch_documentation_page: Fetches content from a documentation URL as markdown
- url (string, required): The URL to fetch content from
fetch_document_links: Fetches all links from a documentation page
- url (string, required): The URL to fetch links from

Usage Examples

To use Docy effectively with Claude, include these prompts:

# Verify implementation against documentation
Are we implementing Crawl4Ai scrape results correctly? Let's check the documentation.

# Explore API usage patterns
What do the docs say about using mcp.tool? Show me examples from the documentation.

# Compare implementation options
How should we structure our data according to the React documentation? What are the best practices?

To ensure Claude prioritizes Docy, add these guidelines to your CLAUDE.md file:

## Documentation Guidelines
- When checking documentation, prefer using Docy over WebFetchTool
- Use list_documentation_sources_tool to discover available documentation sources
- Use fetch_documentation_page to retrieve full documentation pages
- Use fetch_document_links to discover related documentation

Troubleshooting

If you encounter "Tool not found" errors in Claude Code CLI:

Create a .docy.urls file with your documentation URLs
Run the server with SSE transport:

docker run -i --rm -p 8000:8000 \
  -e DOCY_TRANSPORT=sse \
  -e DOCY_HOST=0.0.0.0 \
  -e DOCY_PORT=8000 \
  -v "$(pwd)/.docy.urls:/app/.docy.urls" \
  oborchers/mcp-server-docy

Configure Claude Code .mcp.json to use the SSE endpoint:

{
  "mcp": {
    "servers": {
      "docy": {
        "type": "sse",
        "url": "http://localhost:8000/sse"
      }
    }
  }
}

Caching Behavior

Docy automatically caches documentation content:

Pre-fetches and caches configured documentation URLs at startup
Cache TTL is configurable via DOCY_CACHE_TTL
New sites accessed are automatically cached
Cache persists between server restarts
The .docy.urls file is re-read on each request to support hot-reloading

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

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

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect