Python Interpreter MCP Server

@bimalpaudels

Repository

Basic information

About Python Interpreter MCP Server

A Model Context Server providing simple features to automate python script execution via LLMs.

#python #automation #llm #mcp-server

Python Interpreter MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

Python Interpreter MCP Server tools

Runs the given script with `uv run script.py`.

Overview

What is Python Interpreter Mcp?

Python Interpreter Mcp is a lightweight, experimental MCP server designed to execute arbitrary Python scripts in a structured and reproducible environment. It leverages uv to run isolated code snippets through subprocesses.

How to use Python Interpreter Mcp?

Install via uvx and configure in your MCP client. For example, add {"command": "uvx", "args": ["python-interpreter-mcp"]} to your Claude Desktop config, or use the MCPServerStdio class with the OpenAI Agents SDK. The server exposes a single tool run_script that takes a code string and returns the script’s stdout.

Key features of Python Interpreter Mcp

Executes arbitrary Python scripts with uv run for dependency isolation
Saves scripts to a hidden folder in the current working directory
Lightweight, single-tool interface (run_script)
Designed for structured and reproducible execution
Experimental – use only in trusted, sandboxed environments

Use cases of Python Interpreter Mcp

Running user-provided Python snippets via an LLM or MCP client
Safely testing short scripts inside an isolated subprocess
Integrating code execution into AI workflows (e.g., OpenAI Agents SDK)
Prototyping a sandboxed Python interpreter for development or education

Frequently asked questions

How does Python Interpreter Mcp run scripts?

It receives a script string, saves it as a `.py` file inside a hidden folder in the current working directory, then executes it with `uv run` to ensure dependency isolation. The stdout is captured and returned.

What tool does Python Interpreter Mcp provide?

It provides a single MCP tool named `run_script` which takes a `code` (string) input and returns the script’s stdout.

Are there any security concerns?

Yes – the server executes arbitrary Python code, which can run anything including malicious commands. It should only be used in trusted, sandboxed environments, and inputs must be validated and guardrailed when used with an LLM.

What runtime dependencies does Python Interpreter Mcp require?

It requires **uv** (the Python package installer from Astral) to run scripts via subprocesses.

Is Python Interpreter Mcp production‑ready?

No – this project is in a very early stage of development and is experimental.

Comments

More Other MCP servers

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea