MCP Catalogs
Homemindbridge-mcp screenshot

mindbridge-mcp

by pinkpixel-dev·34·Score 44

MindBridge is an AI orchestration MCP server that unifies access to multiple LLM providers through a single API.

ai-llmdeveloper-toolsproductivity
8
Forks
2
Open issues
2 mo ago
Last commit
2d ago
Indexed

Overview

MindBridge is a sophisticated MCP server designed to unify and orchestrate interactions with multiple large language model providers. It supports OpenAI, Anthropic, DeepSeek, Google, Ollama, and OpenAI-compatible APIs, allowing users to route queries, compare models, and build complex multi-LLM workflows. The server provides smart routing capabilities, automatically detecting providers and offering specialized tools like 'getSecondOpinion' for comparing model responses. Its architecture emphasizes flexibility, supporting configuration through environment variables, MCP configuration, or JSON files.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Building agent systems that need to leverage multiple LLM providers simultaneously
you:Creating AI orchestration engines that intelligently route queries to specialized models
you:Developing reasoning-heavy applications that compare multiple model outputs
you:What LLM providers does MindBridge support?
you:How does the getSecondOpinion tool work?

When to choose this

Choose MindBridge when you need to orchestrate multiple LLM providers or compare model outputs for critical tasks, especially if you're already using multiple AI services and want a unified interface.

When NOT to choose this

Avoid if you need maximum security control over your LLM interactions or are looking for a lightweight solution with minimal dependencies.

Tools this server exposes

3 tools extracted from the README
  • getSecondOpinion{provider: string, model: string, prompt: string, systemPrompt?: string, temperature?: number, maxTokens?: number, reasoning_effort?: 'low' | 'medium' | 'high'}

    Get responses from multiple LLM models to compare answers side-by-side

  • listProviders

    List all configured LLM providers and their available models

  • listReasoningModels

    List models optimized for reasoning tasks

Comparable tools

llamafile-mcplmstudio-mcpopenai-mcp

Installation

Installation

Option 1: Install from npm
# Install globally
npm install -g @pinkpixel/mindbridge

# use with npx
npx @pinkpixel/mindbridge
Option 2: Install via Smithery
npx -y @smithery/cli install @pinkpixel-dev/mindbridge-mcp --client claude
Option 3: Install from source
git clone https://github.com/pinkpixel-dev/mindbridge.git
cd mindbridge
chmod +x install.sh
./install.sh
cp .env.example .env
Claude Desktop Configuration

Add this to your Claude Desktop configuration file:

{
  "mcpServers": {
    "mindbridge": {
      "command": "npx",
      "args": [
        "-y",
        "@pinkpixel/mindbridge"
      ],
      "env": {
        "OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
        "ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY_HERE"
      }
    }
  }
}

FAQ

What LLM providers does MindBridge support?
MindBridge supports OpenAI, Anthropic, Google, DeepSeek, OpenRouter, Ollama (local models), and any OpenAI-compatible API endpoints.
How does the getSecondOpinion tool work?
The getSecondOpinion tool allows you to send the same prompt to multiple models simultaneously, providing side-by-side comparisons of their responses to help determine which model performs better for your specific use case.

Compare mindbridge-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.