Sandbox MCP
S

Sandbox MCP

Sandbox MCP is a model context protocol server that allows LLMs to run code in secure Docker containers, solving the security problem of the inability to test code generated by AI.
2.5 points
10.0K

What is Sandbox MCP?

Sandbox MCP is a Model Context Protocol (MCP) server that provides a secure code execution environment for AI models. It allows AI models (such as Claude, Cursor, etc.) to run code in isolated Docker containers without affecting your host system.

How to use Sandbox MCP?

Simply install Sandbox MCP and configure your AI client, and the AI can automatically test code in a secure environment. You don't need to manually copy and paste code or worry about security issues.

Applicable scenarios

When you use AI to generate code, especially system commands, scripts, or code that requires dependencies, Sandbox MCP can ensure that the code is tested in a securely isolated environment.

Main features

Multi - language support
Supports multiple programming languages such as Python, JavaScript, Go, and Shell
Secure isolation
All code runs in Docker containers, completely isolated from the host
Network control
You can choose to enable or disable network access to meet different security requirements
Customizable sandbox
Supports adding custom sandbox environments to meet specific needs
Advantages
Improve the accuracy and reliability of code generated by AI
Avoid potential security risks and protect your host system
Reduce the workload of manual testing and improve efficiency
Flexible configuration options to meet different needs
Limitations
Requires a Docker environment to be installed
May be limited in some high - performance computing scenarios
Cannot access external resources in network isolation mode

How to use

Install Sandbox MCP
Download the binary file suitable for your operating system or install it via Go
Initialize the configuration
Create a configuration directory and pull the default sandbox
Configure the AI client
Add Sandbox MCP server information to the AI client configuration file

Usage examples

Python code testing
Automatically test Python code generated by AI in an isolated environment
Shell command verification
Verify whether the Shell commands recommended by AI are safe and effective

Frequently Asked Questions

Which AI clients does Sandbox MCP support?
How to add a custom sandbox environment?
Is there a time limit for running code?

Related resources

GitHub repository
Project source code and the latest version
Codapi project
The project that inspired this one
Demo video
A demonstration of the actual use of Sandbox MCP

Installation

Copy the following command to your Client for configuration
{
    "mcpServers": {
        "sandbox-mcp": {
            "command": "path/to/sandbox-mcp",
            "args": [
                "--stdio"
            ]
        }
    }
}

{
    "mcpServers": {
        "sandbox-mcp": {
            "command": "/path/to/sandbox-mcp/dist/sandbox-mcp",
            "args": [
                "--stdio"
            ]
        }
    }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.5K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.4K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
5.7K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.7K
4 points
P
Paperbanana
Python
7.1K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.8K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.8K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.8K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.2K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.2K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.2K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.2K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.4K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.4K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase