DocsFetcher
Fetches package documentation from various language ecosystems without requiring API keys.
π DocsFetcher MCP Server
An MCP server that fetches package documentation from multiple language ecosystems for LLMs like Claude without requiring API keys.
β¨ Features
- π Supports multiple programming languages (JavaScript, Python, Java, .NET, Ruby, PHP, Rust, Go, Swift)
- π¦ Fetches documentation for packages by name or URL
- π Crawls documentation sites to extract comprehensive information
- π Extracts README, API docs, code examples, and repository info
- π§ Provides structured data for LLM summarization
- π¬ Includes specialized prompts for documentation analysis
- π No API key required - works natively with Claude Desktop and Cursor IDE
π Installation
Claude Desktop
- Open Claude Desktop β Settings β Developer
- Click "Edit Config" and add:
{
"mcpServers": {
"docsFetcher": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@cdugo/mcp-get-docs",
"--config",
"'{}'"
]
}
}
}
Cursor IDE Configuration
- Open Cursor IDE β Settings β MCP -> Add New MCP Servier
- Add:
Name: docsFetcher
Command: npx -y @smithery/cli@latest run @cdugo/mcp-get-docs --config "{}"
Prerequisites
- π Node.js 18 or later
πββοΈ Running Locally
git clone https://github.com/cdugo/package-documentation-mcp
cd package-documentation-mcp
npm install
npm run build
Once installed, you can run the server locally with:
# From the project root directory
npm start
For development with auto-restart on file changes:
npm run dev
The server will start on the default port (usually 3000). You should see output like:
π DocsFetcher MCP Server running!
π Ready to fetch documentation
To specify a custom port:
PORT=8080 npm start
π οΈ Available Tools
- fetch-url-docs: π Fetch docs from a specific URL
- fetch-package-docs: π¦ Fetch docs for a package with optional language specification
- fetch-library-docs: π§ Smart tool that works with either package name or URL
- fetch-multilingual-docs: π Fetch docs for a package across multiple language ecosystems
π Available Prompts
- summarize-library-docs: π Create a comprehensive library summary
- explain-dependency-error: π Generate dependency error explanations
π‘ Example Queries
Basic Library Information
- "What is Express.js and how do I use it?"
- "Tell me about the React library"
- "How do I use requests in Python?"
Multi-language Support
- "Show me documentation for lodash in JavaScript"
- "Compare pandas in Python and data.table in R"
Using Tools
- "@fetch-package-docs with packageName='express' and language='javascript'"
- "@fetch-package-docs with packageName='requests' and language='python'"
- "@fetch-multilingual-docs with packageName='http' and languages=['javascript', 'python', 'rust']"
Using Prompts
- "@summarize-library-docs with libraryName='express'"
- "@explain-dependency-error with packageName='dotenv'"
β Troubleshooting
Local Installation
- Server not showing up: β Verify absolute path in configuration
- Connection errors: π Restart Claude Desktop or Cursor IDE
- Fetch failures: β οΈ Some packages may have non-standard documentation
- Language support: π If a language isn't working, try using the package's direct URL
π License
MIT
Related Servers
gluestack-ui MCP Server
An MCP server tailored for React Nativeβfirst development using Gluestack UI
Figma MCP Server
Connects to the Figma API, allowing AI tools to access and interact with your Figma designs.
OPNsense MCP Server
A comprehensive MCP server for managing OPNsense firewalls, offering over 300 tools for configuration and monitoring.
Authless Remote MCP Server
An authentication-free remote MCP server designed for deployment on Cloudflare Workers.
VSCode MCP Server
A VSCode extension that acts as an MCP server, providing access to diagnostic tools and debug session management.
nf-core MCP Server
Manage and navigate local nf-core pipeline repositories.
DeepWiki by Devin
Remote, no-auth MCP server providing AI-powered codebase context and answers
Code Runner MCP
Execute JavaScript and Python code in a secure sandbox. Supports Deno for JS/TS and Pyodide for Python, with configurable permissions.
Supervisord MCP
A tool for managing Supervisord processes, integrated with AI agents via the Model Context Protocol (MCP). It offers standardized process control, real-time monitoring, and robust operations.
Intervals.icu
Connects to the Intervals.icu API to retrieve activities, events, and wellness data.