Python Interpreter Mcp
About
A Model Context Server providing simple features to automate python script execution via LLMs.
Details
- License
- MIT license
Explore
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Python Interpreter McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
async with MCPServerStdio(
params={
"command": "uvx",
"args": ["python-interpreter-mcp"],
}
) as server
...
Add this to your claude_desktop_config.json:
"mcpServers": {
"interpreter": {
"command": "uvx",
"args": ["python-interpreter-mcp"]
}
}
This project is in a very early stage of development.
run_script
Runs the given script with `uv run script.py`.
code
(str): Script to be run
- run_script
- Runs the given script with uv run script.py.
- Input:
- code(str): Script to be run
- Return: The stdout of the given script.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"python interpreter mcp": {
"interpreter": {
"command": "uvx",
"args": [
"python-interpreter-mcp"
]
}
}
}
}McpServers
{
"interpreter": {
"command": "uvx",
"args": [
"python-interpreter-mcp"
]
}
}Overview
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.Tools
-run_script
- Runs the given script with uv run script.py.
- Input:
- code(str): Script to be run
- Return: The stdout of the given script.
Configuration
Usage with OpenAI Agents SDK
async with MCPServerStdio(
params={
"command": "uvx",
"args": ["python-interpreter-mcp"],
}
) as server
...
Usage with Claude Desktop
Add this to yourclaude_desktop_config.json:
"mcpServers": {
"interpreter": {
"command": "uvx",
"args": ["python-interpreter-mcp"]
}
}
How it works
- A script string is received by the MCP tool run_script.
- A hidden folder is created in cwd, and the script is saved as a .py file inside it.
- The script is then executed using uv run, which ensures dependency isolation.
- The stdout of the script is captured and returned as the response.
Usage Warnings
This project is in a very early stage of development.⚠️ Important notes
- It executes arbitrary Python code, which means it can run anything — including malicious or destructive commands. - Use only in trusted, sandboxed environments. - You should always validate, guardrail, or restrict inputs when wiring this into an LLM.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
