What is Mcp Python Helper

mcp-python-helper is a tool designed to assist with Python projects, specifically in the context of the Model Context Protocol (MCP) servers. It simplifies the management and operation of Python packages within the MCP ecosystem.

Use cases

It can be used for developing and publishing Python packages, syncing dependencies, building distributions, and debugging applications running as MCP servers. This makes it useful for developers looking to streamline their workflow in a Python-based MCP environment.

How to use

To use mcp-python-helper, you need to configure it in the Claude Desktop application by specifying the command and arguments for your MCP server. You can then install, build, and publish packages using command-line instructions provided in the documentation.

Key features

Key features include syncing dependencies, building source and wheel distributions, publishing to PyPI, and an integrated debugging experience via the MCP Inspector. It also includes customized server configurations for development and published servers.

Where to use

mcp-python-helper can be used in any environment where Python projects are being developed, particularly those that interface with Model Context Protocol servers. It’s valuable on both MacOS and Windows platforms, offering a cross-platform solution for Python developers.

mcp-python-helper MCP server

Tools to help with python projects

Components

Tools

WIP

Configuration

WIP

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration

``` "mcpServers": { "mcp-python-helper": { "command": "uv", "args": [ "--directory", "/path/to/mcp-python-helper", "run", "mcp-python-helper" ] } } ```

Published Servers Configuration

``` "mcpServers": { "mcp-python-helper": { "command": "uvx", "args": [ "mcp-python-helper" ] } } ```

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You’ll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/phil/dev/mcp-python-helper run mcp-python-helper

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.