Python

Python interpreter, MCP server, no API key, free. Get results from running Python code. Python代码解释器MCP，功能包括：执行python代码，运行python库安装，运行python脚本。

python

8

GitHub Stars

python

Language

6 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": {
    "shibing624-mcp-run-python-code": {
      "command": "uvx",
      "args": [
        "mcp-run-python-code"
      ]
    }
  }
}

You can run practical Python scripting workflows through an MCP server that lets you execute Python code, install packages, save code to files, and run existing Python scripts. It’s designed to integrate with MCP clients and supports safe code execution, on-demand package installation, and retrieving specific results from executed code.

How to use

You interact with the MCP server by starting it in stdio mode and then sending requests through an MCP client. You can execute Python code directly, save code to a file and run it, install packages with pip, and run existing Python files. You can also request a particular variable value from the executed code and receive structured results or error messages to aid debugging.

How to install

Prerequisites you need on your machine before starting the MCP server:

Python is installed on your system (recommended versions depend on your code).
pip is available for installing Python packages.
A compatible MCP client is available to send requests to the server.

Running the MCP server locally

You can run the MCP server in stdio transport mode using one of the provided commands. Choose the command that fits your setup.

uvx mcp-run-python-code

uv run mcp-run-python-code

python -m mcp-run-python-code

Running the FastAPI server for HTTP endpoints

If you prefer HTTP endpoints for executing Python code, you can run the FastAPI server variant. It exposes health checks and endpoints to execute code, save code to a file, install packages, and run files.

python run_python_code/fastapi_server.py

Using with Cursor

To connect with a Cursor MCP client, run the stdio MCP server variant as shown above. Cursor will communicate with the server through the stdio transport.

Examples

Basic code execution, saving and running a file, and installing a Python package are demonstrated through simple workflows.

Running with Docker

Build and run a Docker container for the MCP server. You can also run the FastAPI variant in a separate container.

Available tools

RunPythonCode

Execute Python code in a safe environment and return print output or error messages.

save_to_file_and_run

Save Python code to a file and execute it, returning a specified variable value.

pip_install_package

Install Python packages using pip.

run_python_file

Run an existing Python file and optionally return a variable value from its execution.