The 302AI Sandbox MCP Server allows AI assistants to safely execute arbitrary code and commands in isolated Linux environments (sandboxes).
Key capabilities:
π Create and manage sandboxes: Create isolated environments, list existing ones, and destroy them when no longer needed
π» Execute code: Run code in multiple languages (Python, R, Java, Bash, JS) with timeout and environment variable support
π₯ Run commands: Execute Linux command line commands in sandboxes
π File management: Import files from public URLs, list files/directories, and export files to downloadable URLs
π Direct code execution: Automatically create, execute, and destroy sandboxes in a single operation
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@302AI Sandbox MCP Serverrun Python code to calculate factorial of 5"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π€ 302AI Sandbox MCP Serverπβ¨

Previews
Here are some usage examples


Here is the list of supported tools

Related MCP server: Gemini MCP Server
β¨ Features β¨
π§ Dynamic Loading - Automatically update tool list from remote server.
π Multi modes supported, you can use
stdinmode locally, or host it as a remote HTTP server
π Tool List
Development
Install dependencies:
npm installBuild the server:
npm run buildFor development with auto-rebuild:
npm run watchInstallation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"302ai-sandbox-mcp": {
"command": "npx",
"args": ["-y", "@302ai/sandbox-mcp"],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}To use with Cherry Studio, add the server config:
{
"mcpServers": {
"Li2ZXXJkvhAALyKOFeO4N": {
"name": "302ai-sandbox-mcp",
"description": "",
"isActive": true,
"registryUrl": "",
"command": "npx",
"args": [
"-y",
"@302ai/sandbox-mcp@0.2.0"
],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}To use with ChatWise, copy the following content to clipboard
{
"mcpServers": {
"302ai-sandbox-mcp": {
"command": "npx",
"args": ["-y", "@302ai/sandbox-mcp"],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}Go to Settings -> Tools -> Add button -> Select Import from Clipboard

Find Your 302AI_API_KEY here
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
β¨ About 302.AI β¨
302.AI is an enterprise-oriented AI application platform that offers pay-as-you-go services, ready-to-use solutions, and an open-source ecosystem.β¨
π§ Integrates the latest and most comprehensive AI capabilities and brands, including but not limited to language models, image models, voice models, and video models.
π Develops deep applications based on foundation models - we develop real AI products, not just simple chatbots
π° Zero monthly fee, all features are pay-per-use, fully open, achieving truly low barriers with high potential.
π Powerful management backend for teams and SMEs - one person manages, many people use.
π All AI capabilities provide API access, all tools are open source and customizable (in progress).
π‘ Strong development team, launching 2-3 new applications weekly, products updated daily. Developers interested in joining are welcome to contact us.
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.