MCP Sandbox
@JohanLi233
About MCP Sandbox
Python sandboxes for llms
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-sandbox": {
"command": "uv",
"args": [
"venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Sandbox?
MCP Sandbox is a Python MCP server that enables users and LLMs to safely execute Python code and install packages in isolated Docker containers. It is designed for developers who need a secure, interactive Python runtime accessible via the Model Context Protocol.
How to use MCP Sandbox?
Clone the repository, install dependencies using uv venv and uv sync, then start the server with uv run main.py. Configuration (host, port, PyPI mirror) can be customized in config.toml. The default SSE endpoint is http://127.0.0.1:8181/sse. For Claude Desktop, configure via supergateway pointing to the SSE URL, optionally including an API key if authentication is enabled.
Key features of MCP Sandbox
- Docker isolation for secure code execution
- Package management with custom PyPI mirrors
- File generation with web link access
- Optional API key authentication
- Built-in web UI for managing sandboxes
- SSE support for real-time MCP integration
Use cases of MCP Sandbox
- Running untrusted Python code in a secure sandbox
- Installing and testing Python packages interactively
- Generating visualizations (e.g., matplotlib plots) and saving them as files
- Creating data files (CSV, Excel) accessible via HTTP links
- Providing a safe Python runtime for LLM agents to execute code
FAQ from MCP Sandbox
What dependencies does MCP Sandbox require?
Python 3.12+, the uv package manager, and Docker.
How does MCP Sandbox communicate with clients?
It uses Server-Sent Events (SSE) for real-time communication; the default endpoint is http://127.0.0.1:8181/sse.
Where is executed code data stored?
Code runs in isolated Docker containers; generated files are stored in the results/ directory and made accessible via direct HTTP links.
Is authentication supported?
Yes, optional API key-based authentication can be enabled for multi-user environments.
What tools does MCP Sandbox provide?
Tools include create_sandbox, list_sandboxes, execute_python_code, install_package_in_sandbox, check_package_installation_status, execute_terminal_command, and upload_file_to_sandbox.
Frequently asked questions
What dependencies does MCP Sandbox require?
Python 3.12+, the uv package manager, and Docker.
How does MCP Sandbox communicate with clients?
It uses Server-Sent Events (SSE) for real-time communication; the default endpoint is `http://127.0.0.1:8181/sse`.
Where is executed code data stored?
Code runs in isolated Docker containers; generated files are stored in the `results/` directory and made accessible via direct HTTP links.
Is authentication supported?
Yes, optional API key-based authentication can be enabled for multi-user environments.
What tools does MCP Sandbox provide?
Tools include `create_sandbox`, `list_sandboxes`, `execute_python_code`, `install_package_in_sandbox`, `check_package_installation_status`, `execute_terminal_command`, and `upload_file_to_sandbox`.
Basic information
More Reasoning MCP servers
Task Planner MCP Server
CaptainCrouton89An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.
Node Code Sandbox MCP π οΈ
mozicim# π’π Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It allows for on-the-fly npm dependency installation, making it easy to execute code safely and efficient
π’π Node.js Sandbox MCP Server
alfonsograzianoA Node.jsβbased Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
π Aider-MCP: AI Coding Server with Universal Auto-Detection
jacv888Aider-MCP-Upgraded is a production-grade multi-agent AI coding system that combines Desktop Commander (DC) investigation capabilities with Aider's implementation power. Features 70%+ token reduction, modular architecture, and intelligent workflow automation through strategic agen
Unified MCP Suite
Godzilla675A suite of Model Context Protocol (MCP) servers designed to enhance AI agent capabilities. Provides tools for media search/understanding (images, video), web information retrieval, PDF generation, and PowerPoint presentation creation, enabling agents to interact with diverse data
Comments