Ollama / vLLM Bridge MCP Server

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

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.

этот файл ставится пользователю, но в репозитории его нет

    result = subprocess.run(

    env = dict(os.environ)

KEY_DIR="${MM_KEY_DIR:-$HOME/.ssh/modelmanager}"

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 mcp-ollama-vllm -- uvx mcp-ollama-vllm

{
  "mcpServers": {
    "mcp-ollama-vllm": {
      "args": [
        "mcp-ollama-vllm"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.mcp-ollama-vllm]
command = "uvx"
args = ["mcp-ollama-vllm"]

{
  "mcpServers": {
    "mcp-ollama-vllm": {
      "args": [
        "mcp-ollama-vllm"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "mcp-ollama-vllm": {
      "args": [
        "mcp-ollama-vllm"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: LOCAL_BACKEND (Backend to use: ollama, vllm or openai), LOCAL_HOST (Model endpoint URL; must be local or on your own network. Required for the openai backend), LOCAL_API_KEY (Optional bearer token, openai backend only; sent as a header, never logged), LOCAL_TIMEOUT (Read timeout in seconds), LOCAL_EMBED_MODEL (Default embedding model), LOCAL_EMBED_PATH (Optional, openai backend only: embedding endpoint path), LOCAL_SCHEMA_MODE (Optional, openai backend only: auto, response_format or none). The author declared them in the registry entry; get the values from the project itself.