MCP-LLM Bridge is a TypeScript middleware that connects local LLMs running via Ollama to the Model Context Protocol (MCP) ecosystem. It translates between LLM outputs and MCP's JSON-RPC protocol, enabling open-source models to use external tools and services just like cloud-based assistants. Key features: - Connects Ollama-compatible models to multiple MCP servers including filesystem access, Brave web search, GitHub operations, memory persistence, Flux image generation, and Google Drive/Gmail integration - Provides dynamic tool routing and structured output validation for reliable execution - Offers multi-server MCP orchestration through a unified local endpoint - Supports configuration-driven setup with credential management for each service - Includes robust process management, automatic tool detection from prompts, and detailed logging

MCP-LLM Bridge

A TypeScript implementation that connects local LLMs (via Ollama) to Model Context Protocol (MCP) servers. This bridge allows open-source models to use the same tools and capabilities as Claude, enabling powerful local AI assistants.

Overview

This project bridges local Large Language Models with MCP servers that provide various capabilities like:

The bridge translates between the LLM's outputs and the MCP's JSON-RPC protocol, allowing any Ollama-compatible model to use these tools just like Claude does.

Current Setup

Architecture

Key Features

Setup

1. Install Ollama and required model:

ollama pull qwen2.5-coder:7b-instruct

2. Install MCP servers:

npm install -g @modelcontextprotocol/server-filesystem
npm install -g @modelcontextprotocol/server-brave-search
npm install -g @modelcontextprotocol/server-github
npm install -g @modelcontextprotocol/server-memory
npm install -g @patruff/server-flux
npm install -g @patruff/server-gmail-drive

3. Configure credentials: - Set BRAVE_API_KEY for Brave Search - Set GITHUB_PERSONAL_ACCESS_TOKEN for GitHub - Set REPLICATE_API_TOKEN for Flux - Run Gmail/Drive MCP auth: node path/to/gmail-drive/index.js auth - For example node C:\Users\patru\AppData\Roaming\npm\node_modules\@patruff\server-gmail-drive\dist\index.js auth

Configuration

The bridge is configured through bridge_config.json:

Example:

{
  "mcpServers": {
    "filesystem": {
      "command": "node",
      "args": ["path/to/server-filesystem/dist/index.js"],
      "allowedDirectory": "workspace/path"
    },
    // ... other MCP configurations
  },
  "llm": {
    "model": "qwen2.5-coder:7b-instruct",
    "baseUrl": "http://localhost:11434"
  }
}

Usage

1. Start the bridge:

npm run start

2. Available commands: - list-tools: Show available tools - Regular text: Send prompts to the LLM - quit: Exit the program

Example interactions:

> Search the web for "latest TypeScript features"
[Uses Brave Search MCP to find results]
> Create a new folder called "project-docs"
[Uses Filesystem MCP to create directory]
> Send an email to user@example.com
[Uses Gmail MCP to compose and send email]

Technical Details

Tool Detection

Response Processing

Extended Capabilities

This bridge effectively brings Claude's tool capabilities to local models:

All while running completely locally with open-source models.

Future Improvements

Related Projects

This bridge integrates with the broader Claude ecosystem:

The result is a powerful local AI assistant that can match many of Claude's capabilities while running entirely on your own hardware.