Pypreader

Provides a bridge to inspect installed Python packages by exposing descriptions, directories, and source code via MCP.

javascript

4

GitHub Stars

javascript

Language

5 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": {
    "zakahan-pypreader-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/zakahan/pypreader-mcp.git",
        "pypreader-mcp"
      ],
      "env": {
        "CURRENT_PYTHON_PATH": "<your-python-path>",
        "CURRENT_LOGGING_LEVEL": "INFO"
      }
    }
  }
}

You run pypreader MCP to let AI agents inspect your local Python environment by exposing package descriptions, file structures, and source code through MCP endpoints. This makes tasks like code analysis, dependency checks, and automated programming assistance more reliable by giving AI models direct access to installed packages.

How to use

You connect an MCP client to the PypReader MCP server to access four core tools. Use these to explore installed Python packages: get_pypi_description to fetch official PyPI descriptions, get_package_directory to list all files in a package, get_source_code_by_path to read a specific file, and get_source_code_by_symbol to fetch a symbol’s definition.

How to install

Prerequisites: ensure you have Node.js and Python installed and available in your environment. You will run the MCP server via uvx using a Git-backed source.

Install uvx if you don’t already have it. 2) Clone the project repository or use the provided MCP command to run it directly from the Git source.

{
  "mcpServers": {
    "PypReader-MCP": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/zakahan/pypreader-mcp.git",
        "pypreader-mcp"
      ],
      "env": {
        "CURRENT_PYTHON_PATH": "<your-python-path>",
        "CURRENT_LOGGING_LEVEL": "INFO"
      }
    }
  }
}

Additional configuration notes

If you use a Python virtual environment, set CURRENT_PYTHON_PATH to the Python executable from that environment. CURRENT_LOGGING_LEVEL can be DEBUG, INFO, WARNING, ERROR, or CRITICAL, with INFO as the default.

Notes on usage and environment

The server reads the active Python environment and exposes tools to inspect PyPI descriptions, package file trees, and source code. Use the environment variables to point to the correct Python executable and to control logging verbosity for troubleshooting.

Available tools

get_pypi_description

Retrieves the official description of a package from PyPI.

get_package_directory

Lists the complete file and directory structure of an installed package.

get_source_code_by_path

Fetches the full source code of a specific file within a package path.

get_source_code_by_symbol

Returns the code snippet defining a specific symbol (function, class, etc.) within a package.