What is Python Sandbox Mcp Server

python_sandbox_mcp_server is a secure server designed to enable Large Language Models (LLMs) to execute Python code safely within isolated Docker containers, ensuring a controlled and safe execution environment.

Use cases

Use cases include running user-generated Python scripts in a controlled environment, generating plots for data visualization, and enabling interactive coding exercises in a secure manner.

How to use

To use python_sandbox_mcp_server, clone the repository, install the required dependencies, pull the Snekbox Docker container, start it with security parameters, and update the MCP server configuration to point to your local build.

Key features

Key features include regular Python code execution with stdout capture, Matplotlib plotting with PNG image generation, secure sandboxing via Snekbox Docker container, and real-time communication using Server-Sent Events (SSE).

Where to use

python_sandbox_mcp_server can be used in fields such as educational platforms, coding assessment tools, and any application requiring safe execution of user-submitted Python code.

Python Sandbox MCP Server

A secure Python code execution server that enables LLMs to run Python code safely in isolated
Docker containers. The server supports:

• Regular Python code execution with stdout capture
• Matplotlib plotting with PNG image generation
• Secure sandboxing via Snekbox Docker container
• Real-time communication using Server-Sent Events (SSE)

Development

To get started with development, follow these steps:

Step 1: Clone the Repository

Fork and clone the repository:

git clone https://github.com/username/python_sandbox_mcp_server.git

Navigate into the project directory:

cd python_sandbox_mcp_server

Step 2: Install Dependencies

Install the required dependencies:

uv add -r requirements.txt

Step 3: Build the Python Sandbox

Pull the Snekbox Container Image:

docker pull ghcr.io/python-discord/snekbox:latest

Start the Container with Security Parameters:

docker run -d --ipc=none --privileged -p 8060:8060 ghcr.io/python-discord/snekbox

Install Additional Dependencies (Optional):

• If additional Python packages are required, you can install them as follows:

docker exec <container_id> /bin/sh -c \
    'PYTHONUSERBASE=/snekbox/user_base /snekbox/python/default/bin/python -m pip install --user <package_name>'

• Replace <container_id> with the ID of your running Snekbox container and <package_name> with the desired package.

Step 4: Update MCP Server Configuration

Update your MCP server configuration to point to the local build:

{
  "mcpServers": {
    "python-sandbox-sse": {
      "command": "mcp-proxy",
      "args": [
        "http://localhost:8060/eval"
      ],
      "ssePath": "/eval"
    }
  }
}

Configuration

The server can be configured through the following environment variables or by modifying the Config class:

• MCP_SERVER_NAME: Server identifier (default: “python-sandbox-mcp-sse”)
• SNEKBOX_URL: Snekbox API endpoint (default: “http://localhost:8060/eval”)
• TEMP_DIR: Directory for temporary files storage

License

MIT License