Skip to content
MCP server

LLM Sandbox

Securely run LLM-generated code in isolated containers across 7 languages and 3…

Runs locallyStatus and history
Install
Pricing
Open source
Runs
Locally
Version
0.3.43
Listing updated
6 days ago

Similar MCP servers

About LLM Sandbox

LLM Sandbox is an open-source MCP server for ai models and llm tooling. It runs locally on your machine and is started by your AI client.

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

Install

Run in a terminal

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

Add to claude_desktop_config.json

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "llm-sandbox"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Using several servers? Build one config file with the MCP config generator.

Configuration

  • BACKENDContainer backend to use. Must match the installed extra: mcp-docker, mcp-podman, or mcp-k8s.
  • DOCKER_HOSTDocker or Podman socket URL, e.g. unix:///var/run/docker.sock
  • KUBECONFIGPath to kubeconfig file when BACKEND=kubernetes.
  • NAMESPACEKubernetes namespace used for sandbox pods when BACKEND=kubernetes.
  • COMMIT_CONTAINERCommit the container after a run so installed libraries persist between sessions.
  • KEEP_TEMPLATEKeep the base image after the session ends to avoid re-pulling it on the next run.
  • SANDBOX_NETWORK_MODENetwork mode for the sandbox container. Set to 'none' for hardened isolation. Docker and Podman backends only.
  • SANDBOX_READ_ONLYMount the sandbox root filesystem read-only. Recommended: true. Docker and Podman backends only.
  • SANDBOX_CAP_DROPComma-separated Linux capabilities to drop. Recommended: ALL. Docker and Podman backends only.
  • SANDBOX_SECURITY_OPTComma-separated container security options, e.g. no-new-privileges. Docker and Podman backends only.
  • SANDBOX_MEMORYMemory limit for the sandbox container, e.g. 4g. Docker and Podman backends only.
  • SANDBOX_CPUSFractional CPU allocation for the sandbox container, e.g. 1.5. Docker and Podman backends only.

Pricing

Open source

Prices change. Check vndee.github.io before you buy.

LLM Sandbox FAQ

Is LLM Sandbox free?

Yes. LLM Sandbox is open source, so you can use and self-host it for free.

How do I add LLM Sandbox to Claude Code?

Run this command in your terminal: claude mcp add llm-sandbox -- uvx llm-sandbox

Where this comes from

  • Description: from the official MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers