Local LLM Worker MCP Server

What the code does

We read the source, 2 d ago · rules ccca72095570

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

      await fs.writeFile(wtTarget, code);

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

      child = spawn(cmd, args, { cwd, env, stdio: ['ignore', 'pipe', 'pipe'] });

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add local-llm-worker -- npx -y local-llm-worker

{
  "mcpServers": {
    "local-llm-worker": {
      "args": [
        "-y",
        "local-llm-worker"
      ],
      "command": "npx"
    }
  }
}

[mcp_servers.local-llm-worker]
command = "npx"
args = ["-y", "local-llm-worker"]

{
  "mcpServers": {
    "local-llm-worker": {
      "args": [
        "-y",
        "local-llm-worker"
      ],
      "command": "npx"
    }
  }
}

{
  "mcpServers": {
    "local-llm-worker": {
      "args": [
        "-y",
        "local-llm-worker"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: LLW_BASE_URL (Model server URL (Ollama, llama.cpp, LM Studio, vLLM). Default http://localhost:11434), LLW_MODEL (Model to use; optional if the server has only one), LLW_SEARCH_URL (SearXNG URL for web research (optional)). The author declared them in the registry entry; get the values from the project itself.