LLM Sandbox

MCP server · by vndee

AI & ML Python v0.3.43

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

View source ↗ Website ↗ Generate config for multiple servers More servers

Install

Pin version registry version 0.3.43

Python
uvx llm-sandbox

Python
uvx llm-sandbox@0.3.43

Setup by client

Pick your client — the config below is generated for this server (local stdio). Copy respects the “Pin version” switch above.

claude_desktop_config.json

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox@0.3.43"
      ]
    }
  }
}

Format verified against the official Claude Desktop docs ↗.

terminal

claude mcp add llm-sandbox -- uvx llm-sandbox

claude mcp add llm-sandbox -- uvx llm-sandbox@0.3.43

Format verified against the official Claude Code docs ↗.

.cursor/mcp.json

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox@0.3.43"
      ]
    }
  }
}

Format verified against the official Cursor docs ↗.

.vscode/mcp.json

{
  "servers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}

{
  "servers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox@0.3.43"
      ]
    }
  }
}

Format verified against the official VS Code docs ↗.

mcp_config.json

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox@0.3.43"
      ]
    }
  }
}

Format verified against the official Windsurf docs ↗.

Environment variables

Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.

BACKEND — Container backend to use. Must match the installed extra: mcp-docker, mcp-podman, or mcp-k8s.
DOCKER_HOST — Docker or Podman socket URL, e.g. unix:///var/run/docker.sock
KUBECONFIG — Path to kubeconfig file when BACKEND=kubernetes.
NAMESPACE — Kubernetes namespace used for sandbox pods when BACKEND=kubernetes.
COMMIT_CONTAINER — Commit the container after a run so installed libraries persist between sessions.
KEEP_TEMPLATE — Keep the base image after the session ends to avoid re-pulling it on the next run.
SANDBOX_NETWORK_MODE — Network mode for the sandbox container. Set to 'none' for hardened isolation. Docker and Podman backends only.
SANDBOX_READ_ONLY — Mount the sandbox root filesystem read-only. Recommended: true. Docker and Podman backends only.

GitHub

⭐ 1,131 stars · 最近更新于 33 天前 · MIT license

About this server

Distributed as Python, listed under AI & ML. Review our MCP security guide before granting access to real data.

Frequently asked questions

How do I install LLM Sandbox?

Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.

Is LLM Sandbox free to use?

The MCP server itself is free to install. The source is public on https://github.com/vndee/llm-sandbox. Any third-party service it calls may require its own API key and account.

Which clients support LLM Sandbox?

Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.

Add this badge

Publish this server? Link back with a badge on your README or site — copy either snippet.

Markdown

[![Listed on MCPNav](https://mcpnav.net/badge/llm-sandbox.svg)](https://mcpnav.net/server/llm-sandbox/)

HTML

<a href="https://mcpnav.net/server/llm-sandbox/"><img src="https://mcpnav.net/badge/llm-sandbox.svg" alt="Listed on MCPNav" height="20"></a>