Skip to content
mcp/harbor
Cursor

Ollama / vLLM Bridge for Cursor

io.github.setheerwagen/mcp-ollama-vllm

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

client:Cursor transport:stdio runtime:pypi

Install Ollama / vLLM Bridge in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

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

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs

Ollama / vLLM Bridge in other clients

Ollama / vLLM Bridge MCP server