Home › Knowledge & Memory › Ollama / vLLM Bridge

Ollama / vLLM Bridge

Call your local Ollama or vLLM model over MCP with schema-validated JSON output

Python Local

★ 0 stars Last pushed 2026-09-08 License: MIT

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 1.0.2)

uvx mcp-ollama-vllm

Or add to your MCP client config:

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

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 secret — 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