MCP Sandbox
About
An interactive sandbox to safely execute Python code and install packages in isolated Docker containers.
Details
- License
- MIT license
Explore
- 🐳 Docker Isolation: Securely run Python code in isolated Docker containers
- 📦 Package Management: Easily install and manage Python packages with support for custom PyPI mirrors
- 📊 File Generation: Support for generating files and accessing them via web links
- 🔐 Authentication: Optional API key-based authentication for multi-user environments
- 🎨 Web UI: Built-in web interface for managing sandboxes and viewing execution results
- 🌐 SSE Support: Real-time communication via Server-Sent Events for MCP integration
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
MCP SandboxCommand (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
uv venv
uv sync
Below is an example config for Claude Desktop:
{
"mcpServers": {
"mcpSandbox": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://127.0.0.1:8181/sse"]
}
}
}
If authentication is enabled, include the API key:
{
"mcpServers": {
"mcpSandbox": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://127.0.0.1:8181/sse?api_key=<YOUR_API_KEY>"]
}
}
}
{
"mcpServers": {
"mcpSandbox": {
"command": "npx",
"args": ["-y", "supergateway", "--sse", "http://115.190.87.78/sse?api_key=<API_KEY>"]
}
}
}
``
Modify the
serverUrl` as needed for your environment.1. create_sandbox: Creates a new Python Docker sandbox and returns its ID for subsequent code execution and package installation
2. list_sandboxes: Lists all existing sandboxes (Docker containers) for reuse
3. execute_python_code: Executes Python code in a specified Docker sandbox
4. install_package_in_sandbox: Installs Python packages in a specified Docker sandbox
5. check_package_installation_status: Checks if a package is installed or installation status in a Docker sandbox
6. execute_terminal_command: Executes a terminal command in the specified Docker sandbox. Parameters: sandbox_id (string), command (string). Returns stdout, stderr, exit_code.
7. upload_file_to_sandbox: Uploads a local file to the specified Docker sandbox. Parameters: sandbox_id (string), local_file_path (string), dest_path (string, optional, default: /app/results).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp sandbox": {
"mcp-sandbox": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"mcp-sandbox": {
"command": "uv",
"args": [
"venv"
]
}
}<p align="center">
</p>
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
