302AI Sandbox MCP Server
About
A code sandbox for AI assistants to safely execute arbitrary code. Requires a 302AI API key for authentication.
Details
- Author
- 302ai
- Downloads
- 653
- Categories
- Developer Tools, AI, Other
Jump to
- Dynamic loading of tool list from remote server.
- Supports both local stdin and remote HTTP modes.
- Create, list, and destroy isolated sandboxes.
- Execute arbitrary code with one-click or run-code tool.
- Run command-line instructions inside the sandbox.
- Import and export files to and from the sandbox.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
302AI Sandbox MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the server via the npm package @302ai/sandbox-mcp and configure it with your 302AI_API_KEY in your MCP client (e.g., Claude Desktop, Cherry Studio, or ChatWise). The server can run in stdin mode locally or be hosted as a remote HTTP server.
downloadSandboxFiles
Export files from a sandbox directory or file path to downloadable urls. Supports batch export of multiple directories or files. When exporting directories, only common file formats are included (documents, images, audio, video, compressed files, web files, and programming language files).
listSandboxes
Query the list of sandboxes associated with the current API key. If no parameters are passed, all current sandboxes will be returned.
createSandbox
Create a Linux sandbox that can execute code, run commands, upload and download files, and has complete Linux functionality. After successful creation, a sandbox_id will be returned, and all subsequent operations will need to include this sandbox_id to specify the corresponding sandbox. After successful creation, the sandbox will automatically pause. When calling other sandbox operation interfaces later, it will automatically reconnect and pause again after execution to avoid generating extra costs.
killSandbox
Destroy a sandbox by its ID.
directRunCode
Automatically creates a sandbox, executes code, and immediately destroys the sandbox after execution. Optionally exports sandbox files (compresses multiple files into a zip archive if there are multiple files in the specified path, or exports a single file directly). Recommended for use cases that don't require continuous sandbox operations.
writeSandboxFiles
Import files from public URLs or base64 data into a sandbox. Supports batch import of multiple files. If the target file already exists, it will be overwritten. If the target directory doesn't exist, it will be automatically created. You must create a sandbox before calling this tool.
runCommand
Run a command line command on a specific linux sandbox. This returns text output only. For operations that generate files, you'll need to use separate file viewing and download endpoints.
runCode
Run code on a specific sandbox. This returns text output only. For operations that generate files, you'll need to use separate file viewing and export endpoints. Default file saving path is /home/user.
listSandboxFiles
List files and directories at specified paths within a sandbox. Supports batch queries with multiple paths. This operation can be used before downloadSandboxFiles to check if the file exists.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"302ai sandbox mcp server": {
"302ai-sandbox-mcp": {
"command": "npx",
"args": [
"-y",
"@302ai/sandbox-mcp"
],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
}McpServers
{
"302ai-sandbox-mcp": {
"command": "npx",
"args": [
"-y",
"@302ai/sandbox-mcp"
],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}An MCP service with code sandbox that allows AI assistants to safely execute arbitrary code.
- 🔧 Dynamic Loading - Automatically update tool list from remote server.
- 🌐 Multi modes supported, you can usestdinmode locally, or host it as a remote HTTP server
- One-click Code Execution
- Create Sandbox
- Query Your Sandbox List
- Destroy Sandbox
- Run-Code
- Run Command Line
- Query File Information at Specified Path
- Import File Data into Sandbox
- Export Sandbox Files
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
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.
Supercharge your Agent with Semantic Code Intelligence and save 💰 in the process!
AI-to-AI code review platform — Claude, Codex, and Gemini cross-check each other via MCP, REST API, and CLI for consensus-based results.
Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.
MCP server to dynamically load Claude Code skills into AI agents
MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.
Exposes local execution of Aider commands as a detached process using MCP.
An MCP server for offloading AI coding tasks to Aider, enhancing development efficiency and flexibility.
Assists AI developers with requirement clarification, module design, and technical architecture.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
