Python Runner MCP Server
About
A Python code execution server built on the FastMCP framework, designed for data science and machine learning workflows. It executes Python code in isolated namespaces and comes with pre-installed libraries such as NumPy, pandas, scikit-learn, Matplotlib, and more.
Explore
- Safe Python Code Execution: Execute Python code in isolated namespaces
- Rich Data Science Libraries: Pre-installed with commonly used data science and machine learning packages
- Real-time Output Capture: Capture standard output, error output, and return values
- MCP Protocol Support: Fully compatible with Model Context Protocol
- Easy to Use: Provides a simple and clean API interface
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 Runner MCP ServerCommand (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
- Python 3.12 or higher
- uv package manager (recommended) or pip
Use uvx to run the server directly without installation: [TODO ..... ]
uvx python-runner
Add the following configuration to your Claude Desktop config file:
{
"mcpServers": {
"python-runner": {
"command": "uvx",
"args": ["python-runner"]
}
}
}
Config file locations:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
This project comes pre-installed with the following commonly used data science and machine learning libraries:
- Data Processing: numpy, pandas, scipy
- Machine Learning: scikit-learn
- Data Visualization: matplotlib, seaborn, plotly
- Scientific Computing: sympy
- Image Processing: pillow
- Network Analysis: networkx
- Interactive Development: jupyter
- HTTP Requests: requests
uv sync
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"python runner mcp server": {
"python_runner_mcp": {
"command": "uvx",
"args": [
"python-runner"
]
}
}
}
}McpServers
{
"python_runner_mcp": {
"command": "uvx",
"args": [
"python-runner"
]
}
}A Python code execution server based on the FastMCP framework, designed specifically for data science and machine learning workflows.
🚀 Features
- Safe Python Code Execution: Execute Python code in isolated namespaces
- Rich Data Science Libraries: Pre-installed with commonly used data science and machine learning packages
- Real-time Output Capture: Capture standard output, error output, and return values
- MCP Protocol Support: Fully compatible with Model Context Protocol
- Easy to Use: Provides a simple and clean API interface
⚡ Quick Start (Recommended)
Use uvx to run the server directly without installation: [TODO ..... ]
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
