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
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:
Build the server:
For development with auto-rebuild:
Installation
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
To use with Cherry Studio, add the server config:
To use with ChatWise, copy the following content to clipboard
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:
The 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.