Python REPL

🚀 Python Local MCP Server

A MCP server that provides an interactive Python REPL (Read-Eval-Print Loop) environment.

🚀 Quick Start

This is a MCP server offering an interactive Python REPL environment, allowing users to execute Python code and access session history.

✨ Features

Resources

The server provides access to the REPL session history:

• Utilize the custom repl:// URI scheme to access session history.
• The history of each session can be viewed as a plain text resource.
• The history displays each executed input code and the corresponding output.

Tools

The server implements a tool:

• python_repl: Execute Python code in a persistent session.
  • Accepts code (Python code to be executed) and session_id (a required parameter).
  • Maintains an independent state for each session.
  • Supports expressions and statements.
  • Captures and returns stdout/stderr output.

📦 Installation

Inside the Application

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

📚 Documentation

Building and Publishing

To prepare a distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the package distribution:

uv build

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

3. Publish to PyPI:

uv publish

Note: You 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 the MCP server runs via stdio, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector using npm with the following command:

npx @modelcontextprotocol/inspector uv --directory /path/to/python_local run python-local

After starting, the Inspector will display a URL that you can access in your browser to start debugging.