Safe Local Python Executor MCP server

This MCP server wraps Hugging Face's LocalPythonExecutor to provide a safer way to run Python code generated by LLMs on your local machine. It offers basic isolation and security without requiring Docker or VMs, making it an excellent option for adding Code Interpreter-like functionality to Claude Desktop or other MCP-compatible clients.

Features and Security

The Safe Local Python Executor provides:

• A run_python tool accessible through MCP
• Safer execution environment compared to direct eval()
• Runs via uv in Python venv
• No file I/O operations allowed
• Restricted import list including only safe modules:
  • collections
  • datetime
  • itertools
  • math
  • queue
  • random
  • re
  • stat
  • statistics
  • time
  • unicodedata

This approach offers a good balance between the convenience of local execution and the security of containerized solutions, building on Hugging Face's work to create a secure Python execution environment for LLM-generated code.

Installation Instructions

Prerequisites

1. Install uv package manager:

   # macOS
   brew install uv
   
   # For other platforms, follow instructions at:
   # https://docs.astral.sh/uv/getting-started/installation/
   

Setting up the MCP Server

1. Clone the repository:

   git clone https://github.com/maxim-saplin/mcp_safe_local_python_executor.git
   cd mcp_safe_local_python_executor
   

2. Start the server:

   uv run mcp_server.py
   

   This will automatically create a virtual environment and install the required dependencies (smolagents, mcp).

Configuring Claude Desktop

1. Make sure you have Claude for Desktop installed (available at https://claude.ai/desktop)

2. Edit your Claude Desktop configuration file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • Or open Claude Desktop -> Settings -> Developer -> click "Edit Config" button

3. Add the following configuration (replace /path/to/mcp_local_python_executor/ with your actual path):

   {
       "mcpServers": {
           "safe-local-python-executor": {
               "command": "uv",
               "args": [
                   "--directory", 
                   "/path/to/mcp_local_python_executor/",
                   "run",
                   "mcp_server.py"
               ]
           }
       }
   }
   

4. Restart Claude Desktop

5. The Python executor tool will now be available in Claude (indicated by a hammer icon in the message input field)

Example Usage

Once configured, you can use the Python executor with prompts such as:

• "Calculate the factorial of 5 using Python"
• "Create a list of prime numbers up to 100"
• "Solve this equation (use Python): x^2 + 5x + 6 = 0"

Claude will use the Safe Local Python Executor to run the code and show you the results.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.