Python Sandbox MCP Server
About
A MCP server that enables LLMs to run python code safely in isolated Docker containers.
Details
- Author
- cloudywu0410
- GitHub stars
- 3
- Downloads
- 438
- Categories
- Other
Jump to
- Regular Python code execution with stdout capture
- Matplotlib plotting with PNG image generation
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Python Sandbox MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
First, clone the repository and install dependencies using uv add -r requirements.txt. Then pull the Snekbox Docker image and start the container with security parameters. Optionally install additional Python packages inside the container. Finally, update your MCP client configuration to point to the local build, e.g., using mcp-proxy with SSE endpoint http://localhost:8060/eval. The server can be configured via environment variables MCP_SERVER_NAME, SNEKBOX_URL, and TEMP_DIR.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"python sandbox mcp server": {
"python-sandbox-sse": {
"command": "mcp-proxy",
"args": [
"http://localhost:8060/eval"
],
"ssePath": "/eval"
}
}
}
}McpServers
{
"python-sandbox-sse": {
"command": "mcp-proxy",
"args": [
"http://localhost:8060/eval"
],
"ssePath": "/eval"
}
}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
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
