Ollama / vLLM Bridge

Ollama / vLLM Bridge runs locally from a Python package published to PyPI: mcp-ollama-vllm version 1.0.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx mcp-ollama-vllm. It reads these environment variables: LOCAL_BACKEND, LOCAL_HOST, LOCAL_API_KEY (secret), LOCAL_TIMEOUT, LOCAL_EMBED_MODEL, LOCAL_EMBED_PATH and LOCAL_SCHEMA_MODE; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "mcp-ollama-vllm": {
      "command": "uvx",
      "args": [
        "mcp-ollama-vllm"
      ],
      "env": {
        "LOCAL_BACKEND": "<value>",
        "LOCAL_HOST": "<value>",
        "LOCAL_API_KEY": "<secret>",
        "LOCAL_TIMEOUT": "<value>",
        "LOCAL_EMBED_MODEL": "<value>",
        "LOCAL_EMBED_PATH": "<value>",
        "LOCAL_SCHEMA_MODE": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect