Ollama / vLLM Bridge MCP Server

What this does

Ollama / vLLM Bridge exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation.

Requirements

This server needs the following environment variables to be set before it can run:

LOCAL_BACKEND
LOCAL_HOST
LOCAL_API_KEY
LOCAL_TIMEOUT
LOCAL_EMBED_MODEL
LOCAL_EMBED_PATH
LOCAL_SCHEMA_MODE

Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).

How do I install Ollama / vLLM Bridge?

Run the Claude Code command in the install section to add Ollama / vLLM Bridge to Claude Code, or copy the ready-made config for your client from the install section on this page. Restart your client afterwards and the tools appear in your next conversation.

Which clients work with Ollama / vLLM Bridge?

This page carries setup and config for Claude Code, Claude Desktop, Cursor and VS Code. Any other MCP client that accepts a standard server config can connect to Ollama / vLLM Bridge as well.

Does Ollama / vLLM Bridge need an API key?

Yes. Before it can run, set these environment variables: LOCAL_BACKEND, LOCAL_HOST, LOCAL_API_KEY, LOCAL_TIMEOUT, LOCAL_EMBED_MODEL, LOCAL_EMBED_PATH, LOCAL_SCHEMA_MODE. They go in the env block of your MCP config.