aj-geddes

Quorum MCP — AI skill for Claude Code

AI community

Multi-provider AI consensus orchestration via MCP - Get better answers through deliberation.

How to install Quorum MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aj-geddes/quorum-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Quorum MCP does

Multi-provider AI consensus orchestration via MCP - Get better answers through deliberation.

Alternatives in AI

Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
Orchestration Skills — Multi-agent orchestration patterns 5.3k ★
Golutra — Multi-agent AI orchestration platform for automation, workflows, and developer tools 3.8k ★

README

Quorum-MCP

Multi-AI Consensus System MCP Server - Get better answers through deliberation

[![Tests](https://img.shields.io/badge/tests-105%20passing-success)](https://github.com/aj-geddes/quorum-mcp) [![Coverage](https://img.shields.io/badge/coverage-95%25-brightgreen)](https://github.com/aj-geddes/quorum-mcp) [![Python](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org) [![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE)

🎯 Overview

Quorum-MCP orchestrates multiple AI providers (Anthropic Claude, OpenAI, Google Gemini, Cohere, Mistral AI, Novita AI, Ollama) through multi-round deliberation to produce consensus-based responses. By combining different AI models, you get more balanced, comprehensive, and reliable answers.

**Why Quorum?**

🎭 Diverse Perspectives: Each AI has unique strengths and biases
🤝 Consensus Building: Agreement across models increases confidence
🔍 Quality Assurance: Cross-validation catches errors and hallucinations
💡 Richer Insights: Disagreements reveal nuanced viewpoints

✨ Features

Multi-Provider Support (7 Providers!)

🤖 Anthropic Claude - Thoughtful, nuanced reasoning
- Models: claude-3-5-sonnet-20241022 (default), claude-3-opus, claude-3-haiku
- Context: 200K tokens | Cost: $3-$15/1M input
🧠 OpenAI - Broad knowledge, strong reasoning
- Models: gpt-4o (default), gpt-4o-mini, gpt-4-turbo
- Context: 128K tokens | Cost: $0.15-$30/1M input
✨ Google Gemini - Fast, cost-effective, huge context
- Models: gemini-2.5-flash (default), gemini-2.5-pro, gemini-1.5-pro
- Context: Up to 2M tokens | Cost: $0.15-$1.25/1M input
🏢 Cohere - Enterprise RAG, production-ready
- Models: command-r-plus (default), command-r, command-light
- Context: 128K tokens | Cost: $0.30-$15/1M input
- Features: Excellent RAG capabilities, free tier available
🇪🇺 Mistral AI - Best pricing, European AI
- Models: `