mcp-python-executor

Overview

The MCP Python Executor server provides a secure environment for executing Python code and managing packages. It features safety constraints like memory limits, execution timeouts, and concurrent execution limits. The server supports both inline code execution and script file execution, with options for input data and pre-installed packages. It includes resource monitoring, health checks, and structured logging capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• execute_pythonexecute_python(code?: string, scriptPath?: string, inputData?: string[])

  Execute Python code and return the results.

  Try:Execute this Python code: print('Hello, World')Try:Run the script at /path/to/my_script.pyTry:Process this data with Python code using input ['item1', 'item2']
• install_packagesinstall_packages(packages: string[])

  Install Python packages.

  Try:Install numpy and pandas packagesTry:Add scikit-learn to the current environmentTry:Upgrade matplotlib to the latest version

Comparable tools

Installation

git clone https://github.com/bsmi021/mcp-python-executor.git
cd mcp-python-executor

npm install

npm run build

{
  "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"
      }
    }
  }
}

FAQ

How can I specify custom Python packages to install?

Use the PREINSTALLED_PACKAGES environment variable with space-separated package names, like 'numpy pandas matplotlib'

What happens if my code exceeds the memory limit?

The execution will be terminated automatically and an error message will be returned indicating the memory limit was exceeded

Compare mcp-python-executor with