Enables fetching, exploring, and analyzing source code from Python packages on PyPI, including listing package files, retrieving specific versions, searching for packages, and accessing package metadata.
๐ฆ PyPI Package MCP Server
A powerful Model Context Protocol (MCP) server that enables AI assistants to fetch, explore, and analyze source code from any Python package on PyPI.
โจ Features
๐ฆ Fetch Any PyPI Package: Download and explore source code from millions of packages
๐ Smart File Discovery: List and filter files with intelligent code detection
๐ Selective Code Reading: Get specific files or entire codebases
๐ท๏ธ Version Control: Support for any published package version
๐งน Auto Cleanup: Automatic temporary file management
๐ Type Safe: Full type hints with mypy support
โก Async First: Modern async/await patterns throughout
๐ค AI-Ready: Perfect integration with Claude, ChatGPT, and other AI assistants
๐ฏ Use Cases
Code Analysis: Analyze libraries before adopting them
Learning: Study well-written open source code
AI Development: Enable AI assistants to understand package internals
Documentation: Generate docs by analyzing source code
Security Auditing: Review dependencies for security issues
Migration Planning: Understand APIs when upgrading packages
๐ Installation & Setup
Option 1: Local Development (Stdio Mode)
Option 2: Local Development (HTTP Mode)
Option 3: With Authentication Token
Option 4: Docker (Production - HTTP Mode)
๐ง Configuration
Environment Variables
Variable | Default | Description |
|
| Transport mode:
or
|
|
| HTTP server port (only used in
mode) |
| (none) | Optional authentication token for API access |
Transport Modes
Stdio Mode (Default)
Best for: Claude Desktop, local development
Connection: Standard input/output streams
Command:
pypi-package-mcp-server
HTTP Mode
Best for: Remote servers, containerized deployments
Connection: HTTP requests on specified port
Health endpoint:
GET /healthMCP endpoint:
POST /mcpCommand:
TRANSPORT_MODE=http PORT=3000 pypi-package-mcp-server
Authentication
When AUTH_TOKEN environment variable is set, all HTTP requests must include the token in the Authorization header:
๐ Supported Packages
โ All public PyPI packages
โ Any published version
โ Source distributions (
.tar.gz)โ Binary wheels (
.whl)โ Monorepo packages
โ Pure Python and native extensions
๐ฅ Popular Packages to Explore
Try these commands with your AI assistant:
๐ ๏ธ Tools
1. get_pypi_package_code
Fetch source code from a Python package.
2. list_package_files
List all files in a package.
3. get_package_info
Get metadata about a package.
4. search_pypi_packages
Search for packages on PyPI.
๐ Requirements
Python 3.9 or higher
mcp>= 0.1.0requests>= 2.31.0pydantic>= 2.0.0
๐ Authentication (Optional)
Set the AUTH_TOKEN environment variable for API authentication:
๐งช Development
Install Development Dependencies
Run Tests
Format Code
Lint Code
Type Checking
๐ Troubleshooting
Package Not Found
Verify the package name is correct (use lowercase, hyphens not underscores)
Search first with
search_pypi_packagesto find the exact name
Extraction Failed
Some packages may not have source distributions
Check if a wheel-only package is available
Timeout Issues
Large packages may take time to download
Increase timeout values if needed
๐ Related Projects
๐ License
MIT License - See LICENSE file for details
๐ค Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
โญ Credits
Inspired by the NPM Package MCP Server
Made with โค๏ธ
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Enables AI assistants to fetch, explore, and analyze source code from any Python package on PyPI, including listing files, reading specific code, and searching packages across all published versions.