Code Sandbox MCP

🚀 Code Sandbox MCP 🐳

A secure and isolated environment based on Docker containers for executing code in AI applications. This MCP server provides a secure and isolated environment through containerization technology, ensuring security when running code.

🚀 Quick Start

This Code Sandbox MCP offers a secure and isolated environment for code execution in AI applications. With flexible container management and support for custom environments, it's a powerful tool for developers.

✨ Features

• Flexible Container Management: Create and manage isolated Docker containers for code execution.
• Custom Environment Support: Use any Docker image as the runtime environment.
• File Operations: Easily transfer file directories between the host and containers.
• Command Execution: Run arbitrary shell commands in the containerized environment.
• Real-time Logging: Stream container logs and command outputs in real-time.
• Automatic Updates: Built-in update checks and automatic binary updates.
• Multi-platform Support: Works on Linux, macOS, and Windows.

📦 Installation

Prerequisites

• Docker must be installed and running.
  • Install Docker on Linux
  • Install Docker on macOS
  • Install Docker on Windows

Quick Installation

Run the following commands on Linux, macOS, or Windows to download and install Code Sandbox MCP:

# Download the binary for Linux/macOS
wget https://github.com/Automata-Labs/code-sandbox-mcp/releases/download/v1.0.0/code-sandbox-mcp

# Or download the executable for Windows
wget https://github.com/Automata-Labs/code-sandbox-mcp/releases/download/v1.0.0/code-sandbox-mcp.exe

# Set executable permissions for the binary (Linux/macOS only)
chmod +x code-sandbox-mcp

Manual Installation

If you need to manually build Code Sandbox MCP, refer to DEVELOPMENT.md.

🛠️ Available Tools

The following command-line tools can be used to interact with Code Sandbox MCP:

• code-sandbox-mcp: The main executable for starting and managing the code sandbox service.

Tool Parameters

Example Configuration

{
    "containerImage": "docker.io/library/ubuntu:latest",
    "cpuQuota": 500,
    "memoryLimit": "1G"
}

🔧 Technical Details

Security Features

• Isolated Execution Environment: All code runs in independent Docker containers, ensuring the security of the host system.
• Resource Limitation: Control container resource usage through CPU quotas and memory limits.
• File Isolation: Code and data are only visible inside the container, preventing sensitive information leakage.

Configuration Guide

Configuration on Claude Desktop

The installer will automatically create the configuration file. If you need to configure it manually, refer to the following examples:

Linux

// ~/.config/Claude/claude_desktop_config.json
{
    "mcpServers": {
        "code-sandbox-mcp": {
            "command": "/path/to/code-sandbox-mcp",
            "args": [],
            "env": {}
        }
    }
}

macOS

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
    "mcpServers": {
        "code-sandbox-mcp": {
            "command": "/path/to/code-sandbox-mcp",
            "args": [],
            "env": {}
        }
    }
}

Windows

// %APPDATA%\Claude\claude_desktop_config.json
{
    "mcpServers": {
        "code-sandbox-mcp": {
            "command": "C:\\path\\to\\code-sandbox-mcp.exe",
            "args": [],
            "env": {}
        }
    }
}

Other AI Applications

For other AI applications that support MCP servers, configure them to use the code-sandbox-mcp executable as the code execution backend.

Development

If you need to build the project locally or contribute to development, refer to DEVELOPMENT.md.

📄 License

This project is licensed under the MIT License. For details, see the LICENSE file.