Back to browse
GitHub Repository

MCP server for multi-round AI brainstorming debates between multiple models (GPT, DeepSeek, Groq, Ollama, etc.)

61 starsTypeScript

Phone a Friend for Claude Code – GPT, Gemini, DeepSeek via MCP

by spranab·Feb 26, 2026·1 point·0 comments

AI Analysis

●●SolidCrowd PleaserShip It

Claude debates GPT and Gemini in parallel rounds; costs $0.02–0.05 per brainstorm.

Strengths
  • Claude as genuine participant, not orchestrator—reads context and argues its position
  • Parallel execution and resilience—one model failing doesn't break the debate
  • Low cost per session with clear token estimation and synthesizer fallback
Weaknesses
  • Requires API keys for multiple services; setup friction for casual users
  • Multi-model debate as a concept already exists (perplexity, research tools); execution is solid but not novel
Target Audience

Claude Code users seeking multi-perspective brainstorming and debate synthesis

Similar To

Perplexity research · OpenAI Canvas multi-model · Consensus AI

Post Description

I built an MCP server that gives Claude Code a "phone a friend" lifeline. Instead of relying on one model's perspective, Claude can pull in GPT, Gemini, DeepSeek, or any OpenAI-compatible model for a structured multi-round debate — and participate as an active debater itself.

How it works:

You ask Claude to brainstorm a topic All configured models respond in parallel (Round 1) Claude reads their responses and pushes back with its own take Models see each other's responses and refine across rounds A synthesizer produces the final consolidated output Claude isn't just orchestrating — it has full conversation context, so it knows what you're working on and argues its position alongside the other models. They genuinely build on and challenge each other's ideas.

A 3-round debate with 3 models costs ~$0.02-0.05. One model failing doesn't kill the debate — results are resilient.

npm: npx brainstorm-mcp GitHub: https://github.com/spranab/brainstorm-mcp Sample debate (GPT-5.2 vs DeepSeek vs Claude): https://gist.github.com/spranab/c1770d0bfdff409c33cc9f985043...

Free, MIT licensed. Works with any OpenAI-compatible API including local Ollama.

Similar Projects

Developer Tools●●Solid

I built a desktop app combining Claude, GPT, Gemini with local Ollama

Hybrid pipeline splits reasoning (cloud) and execution (local), but multi-model orchestration is becoming crowded.

Solve My ProblemSlick
tsunamayo
113mo ago