mcp-python-interpreter

Overview

The MCP Python Interpreter is a robust server that enables AI models to interact with Python environments. It provides comprehensive functionality for code execution in different Python environments, package management, and file operations. The server implements security measures through isolated working directories and file path restrictions, making it suitable for development workflows. The documentation is thorough with clear examples and security considerations outlined.

Try asking AI

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

• list_python_environments

  List all available Python environments (system and conda)

  Try:Show me all available Python environments on my systemTry:List all conda environments
• list_installed_packages

  List packages installed in a specific Python environment

  Try:List all packages installed in my system Python environmentTry:Show me the packages in my conda-base environment
• install_package

  Install a Python package in a specific environment

  Try:Install the requests package in my system Python environmentTry:Add pandas to my conda-base environment
• run_python_code

  Execute Python code in a specific environment

  Try:Run this Python code in my conda-base environment: print('Hello, world!')Try:Calculate 2+2 in my system Python
• run_python_file

  Execute a Python file in a specific environment

  Try:Run data_analysis.py with these arguments: --input=data.csv --output=results.csvTry:Execute my script.py file
• read_file

  Read contents of any file type, with size and safety limits

  Try:Read the contents of my 'data.json' fileTry:Show me what's in my analysis.py file
• write_file

  Create or overwrite files with text or binary content

  Try:Write a new configuration file with these settings...Try:Create a text file with 'Hello World' content
• write_python_file

  Create or overwrite a Python file specifically

  Try:Create a new Python file called 'hello.py' with a function that says helloTry:Write a Python script to process my data
• list_directory

  List Python files in a directory

  Try:Show me all Python files in my current directoryTry:List the .py files in my project folder
• python_function_template

  Generate a template for a Python function

  Try:Create a template for a Python function that processes dataTry:Generate a function template for API calls
• refactor_python_code

  Help refactor Python code

  Try:Refactor this Python function to be more efficientTry:Improve the readability of this code
• debug_python_error

  Help debug a Python error

  Try:Debug this Python error: NameError: name 'x' is not definedTry:Fix the syntax error in my code

Comparable tools

Installation

pip install mcp-python-interpreter

uv install mcp-python-interpreter

{
  "mcpServers": {
    "mcp-python-interpreter": {
        "command": "uvx",
        "args": [
            "mcp-python-interpreter",
            "--dir",
            "/path/to/your/work/dir",
            "--python-path",
            "/path/to/your/python"
        ],
        "env": {
            "MCP_ALLOW_SYSTEM_ACCESS": 0
        },
    }
  }
}

FAQ

What security measures are in place?

The server operates within an isolated working directory specified with --dir parameter, has file size limits (up to 1MB), prevents writes outside the working directory, and includes explicit overwrite protection.

Can I use different Python environments?

Yes, the server lists and allows using different Python environments including system and conda environments through the list_python_environments tool.

Compare mcp-python-interpreter with