Python Interpreter MCP server

The MCP Python Interpreter is a server implementing the Model Context Protocol (MCP) that enables Large Language Models to interact with your Python environments. It allows models to execute code, manage packages, read/write files, and handle various Python-related tasks through a structured interface.

Installation

Install the MCP Python Interpreter using pip:

pip install mcp-python-interpreter

Or with uv:

uv install mcp-python-interpreter

Prerequisites

Before installation, ensure you have the uv tool installed:

For Unix/Linux/macOS:

curl -LsSf https://astral.sh/uv/install.sh | sh

For Windows:

powershell -ExecutionPolicy Bypass -Command "iwr -useb https://astral.sh/uv/install.ps1 | iex"

Setting Up With Claude Desktop

Configuration Steps

1. Install Claude Desktop from claude.ai/download
2. Open Claude Desktop, access the menu and go to Settings
3. Navigate to the Developer tab and click "Edit Config"
4. Add the MCP server configuration to your claude_desktop_config.json:

For macOS/Linux:

{
  "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
        },
    }
  }
}

For Windows:

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

5. Restart Claude Desktop
6. The MCP tools icon should now appear in the chat interface

Important: The --dir parameter is mandatory and specifies the working directory where all files will be saved and executed. This provides security by isolating the server's operations to a specific location.

Available Tools and Features

Environment and Package Management

• list_python_environments: View all available Python environments (system and conda)
• list_installed_packages: See what packages are installed in a specific environment
• install_package: Add new Python packages to an environment

Code Execution

• run_python_code: Execute Python code snippets directly
• run_python_file: Run existing Python script files

File Operations

• read_file: View contents of any file (up to 1MB)
  • Text files shown with syntax highlighting
  • Binary files displayed in hex representation
• write_file: Create or update files with text or binary content
• write_python_file: Specifically for Python files
• list_directory: View all Python files in a directory

Resources

The server provides programmatic access to:

• python://environments: List of available Python environments
• python://packages/{env_name}: Package list for a specific environment
• python://file/{file_path}: Content of a Python file
• python://directory/{directory_path}: Directory listing of Python files

Example Usage Prompts

You can ask Claude to:

• "Show me all available Python environments on my system"
• "Run this Python code: print('Hello, world!')"
• "Create a new file called 'config.json' with these settings..."
• "Read the contents of 'data.py'"
• "Install the pandas package in my base environment"
• "List all packages in my conda environment"
• "Run my analysis.py script with the following arguments..."

Security Considerations

The MCP Python Interpreter includes several security features:

• Operations confined to the specified working directory
• File size limits for reading (1MB)
• Prevented access outside the working directory
• Overwrite protection for files

Always review any code or file operations before allowing execution, especially when dealing with system resources.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "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
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "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
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect