Skip to content

spranab/brainstorm-mcp

v1.1.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 3mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-debate brainstorming claude deepseek groq
+7 more
llm mcp mcp-server model-context-protocol multi-model ollama openai

Summary

AI summary

Claude now participates interactively in brainstorming rounds via a new brainstorm_respond tool.

Full changelog

Interactive Mode — Claude as Active Participant

Claude now participates as a debater alongside external models in every round, rather than just orchestrating.

How it works

  1. brainstorm runs round 1 with external models and returns their responses + a session ID
  2. Claude reads the responses, forms its own perspective, and calls brainstorm_respond
  3. External models see Claude's contribution in the next round and refine
  4. Repeats until all rounds complete, then synthesis runs automatically

New

  • brainstorm_respond tool — Claude submits its contribution each round
  • participate parameter on brainstorm (default: true) — set to false for the original non-interactive mode
  • Session management with 10-minute TTL and automatic cleanup

Backward compatible

  • participate=false gives the exact same behavior as v1.0.x
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track spranab/brainstorm-mcp

Get notified when new releases ship.

Sign up free

About spranab/brainstorm-mcp

Multi-round AI brainstorming debates between multiple models (GPT, Gemini, DeepSeek, Groq, Ollama, etc.). Pit different LLMs against each other to explore ideas from diverse perspectives.

All releases →

Related context

Beta — feedback welcome: [email protected]