MCP Python Executor

🚀 MCP Python Executor

A Model Context Protocol (MCP) server for executing Python code and managing Python packages.

🚀 Quick Start

The MCP Python Executor is a server designed to execute Python code and manage Python packages, offering a range of features to ensure secure and efficient operations.

✨ Features

• Execution of Python code with security constraints.
• Installation and management of Python packages.
• Pre - configuration of commonly used packages.
• Resource monitoring and limitation.
• Health checks and metrics.
• Structured logging.

📦 Installation

This server can be configured via environment variables in the MCP settings:

{
  "mcpServers": {
    "mcp-python-executor": {
      "command": "node",
      "args": ["path/to/python-executor/build/index.js"],
      "env": {
        "PREINSTALLED_PACKAGES": "numpy pandas matplotlib scikit-learn",
        "MAX_MEMORY_MB": "512",
        "EXECUTION_TIMEOUT_MS": "30000",
        "MAX_CONCURRENT_EXECUTIONS": "5",
        "LOG_LEVEL": "info",
        "LOG_FORMAT": "json"
      }
    }
  }
}

Environment Variables

💻 Usage Examples

Basic Usage

1. execute_python

Execute Python code and return the result.

interface ExecutePythonArgs {
  code?: string;          // Python code to execute (inline)
  scriptPath?: string;    // Path to an existing Python script file (alternative to code)
  inputData?: string[];   // Optional input data
}

Example:

// Example with inline code
{
  "code": "print('Hello, World!!')\nfor i in range(3): print(i)",
  "inputData": ["optional", "input", "data"]
}

// Example with script path
{
  "scriptPath": "/path/to/your_script.py",
  "inputData": ["optional", "input", "data"]
}

2. install_packages

Install Python packages.

interface InstallPackagesArgs {
  packages: string[];
}

Example:

// Example: Install multiple packages
{
  "packages": ["numpy", "pandas", "matplotlib", "scikit-learn"]
}

// Example: Install a single package
{
  "packages": ["requests"]
}