Click on "Deploy 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., "@sandbox-mcp run a python script that prints the first 10 Fibonacci numbers"
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.
MCP service that exposes sandboxed code execution tools. Delegates execution to a
sandbox-runner VM running Firecracker microVMs on Proxmox (nested KVM).
Tool | Description |
| Run bash script in isolated microVM |
| Run Python 3 code in isolated microVM |
| Run Node.js code in isolated microVM |
All tools: no network access, 256MB RAM, 0.5 CPU, configurable timeout (default 15s).
Related MCP server: Code Executor MCP Server
Variable | Required | Description |
| Yes | Auth token for MCP clients |
| No | URL of sandbox-runner VM (e.g. |
| No | Bearer token for sandbox-runner auth |
| No | HTTP port (default |
| No | Default execution timeout ms (default |
The service expects a sandbox-runner HTTP API (deployed separately on Proxmox):
POST /run
Body: { lang: "bash" | "python" | "node", code: string, timeoutMs: number }
Response: { stdout: string, stderr: string, exitCode: number, durationMs: number }
GET /health
Response: { status: "ok", poolSize: number, available: number }If SANDBOX_RUNNER_URL is not set, the service starts normally but all tool calls
return a 503 not configured message. The feature flag sandbox_exec should remain
disabled until the runner is deployed.
GET /health — health check, includes runnerConfigured boolean
POST /mcp — MCP JSON-RPC (StreamableHTTP)
GET /mcp — MCP SSE transport
This server cannot be deployed
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.
