Skip to content
mcp/harbor
Verified official

Ollama / vLLM Bridge MCP

v1.0.2

io.github.setheerwagen/mcp-ollama-vllm

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

transport:stdio runtime:pypi
View source

Target client

run in your project directory

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

claude mcp add mcp-ollama-vllm -e LOCAL_BACKEND=<LOCAL_BACKEND> -e LOCAL_HOST=<LOCAL_HOST> -e LOCAL_API_KEY=<LOCAL_API_KEY> -e LOCAL_TIMEOUT=<LOCAL_TIMEOUT> -e LOCAL_EMBED_MODEL=<LOCAL_EMBED_MODEL> -e LOCAL_EMBED_PATH=<LOCAL_EMBED_PATH> -e LOCAL_SCHEMA_MODE=<LOCAL_SCHEMA_MODE> -- uvx mcp-ollama-vllm

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.