Docy gives your AI direct access to the technical documentation it needs, right when it needs it. No more outdated information, broken links, or rate limits - just accurate, real-time documentation access for more precise coding assistance.
Documentation
Docy MCP Server
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.
Using Docy
Here are examples of how Docy can help with common documentation tasks:
Are we implementing Crawl4Ai scrape results correctly? Let's check the documentation.\n\n# Explore API usage patterns
What do the docs say about using mcp.tool? Show me examples from the documentation.\n\n# Compare implementation options
How should we structure our data according to the React documentation? What are the best practices?
With Docy, Claude Code can directly access and analyze documentation from configured sources, making it more effective at providing accurate, documentation-based guidance.
Available Tools
list_documentation_sources_tool
fetch_documentation_page
fetch_document_links
Installation## Using uv (recommended)
When using uv no specific installation is needed.\n\n#### Using PIP
Alternatively you can install mcp-server-docy via pip:
pip install mcp-server-docy
```\n\n#### Using Docker
You can also use 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
The application can be configured using environment variables:
- `DOCY_DOCUMENTATION_URLS`
- `DOCY_CACHE_TTL`
- `DOCY_CACHE_DIRECTORY`
### Local Development
Run in development mode: `fastmcp dev src/mcp_server_docy/__main__.py --with-editable .`
### License
mcp-server-docy is licensed under the MIT License.