Brainstorm
About
Multi-model AI brainstorming MCP server. Orchestrates debates between GPT, Gemini, DeepSeek, and Claude with structured synthesis. Includes instant quick mode, multi-model code review with verdicts, and red-team/Socratic styles. Hosted mode needs zero API keys.
Details
- Author
- spranab
- Downloads
- 233
- Categories
- Productivity, AI, Other
Jump to
- Hosted mode with zero API keys needed
- API mode with parallel execution across providers
- Instant multi-model perspectives in under 10 seconds
- Multi-model code review with severity ratings and verdicts
- Three debate styles: freeform, red-team, Socratic
- 3-bullet synthesis verdicts: Recommendation, Key Tradeoffs, Strongest Disagreement
- Multi-round debates where models critique each other’s responses
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
BrainstormCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with npx -y brainstorm-mcp or npm install -g brainstorm-mcp, then add the server to your .mcp.json (Claude Code) or claude_desktop_config.json (Claude Desktop). Optionally set API keys via environment variables or a config file; hosted mode requires no API keys. Invoke tools such as brainstorm, brainstorm_quick, or brainstorm_review by describing your request to Claude.
brainstorm
Run a multi-round brainstorming debate between multiple AI models. IMPORTANT: Before calling this tool, you MUST ask the user to choose a mode: 1. **API mode** — Calls configured providers. These are either HTTP APIs billed per token (OpenAI, Gemini, DeepSeek, ...) or locally installed agent CLIs such as 'claude' and 'codex', which run on the user's existing subscription at no API cost. Call list_providers to see which of each are available. 2. **Hosted mode** — No API keys needed. You execute prompts using sub-agents with models available in your environment (opus/sonnet/haiku, GPT, Gemini, etc.). Same model can be used multiple times — each run produces different perspectives. Present these two options to the user with a one-liner explanation, then proceed based on their choice. For API mode: set mode='api'. When participate=true (default), YOU also participate as a debater alongside external models via brainstorm_respond. For Hosted mode: set mode='hosted'. Ask the user which models to use, then spawn sub-agents for each model, collect responses, and call brainstorm_collect.
brainstorm_respond
Submit YOUR (Claude's) response for the current round of an interactive brainstorm session. After the brainstorm tool returns external models' responses, call this tool with your substantive contribution. Read all responses carefully and engage with specific points — agree, disagree, build upon, or challenge ideas. Do not just summarize. After your response, the next round runs automatically (or synthesis if final round).
brainstorm_collect
Submit collected model responses for a hosted brainstorm session. After receiving prompts from `brainstorm` (mode='hosted') or a previous `brainstorm_collect` call, execute each prompt by spawning a sub-agent for EACH model (use the model parameter to select the right model, e.g., model='sonnet' or model='haiku'). Collect all responses and submit them here. This tool returns either: (1) the next round's prompt to execute, (2) a synthesis prompt for a single model, or (3) the final formatted debate result when complete.
brainstorm_quick
Get instant multi-model perspectives on any question — no debate rounds, no synthesis delay. Fires all models in parallel and returns a compact comparison. Under 10 seconds. Use this for quick second opinions, snap decisions, or when you want diverse perspectives fast. For deeper analysis with multiple rounds and synthesis, use the `brainstorm` tool instead.
brainstorm_review
Multi-model code review. Pass a diff and get structured findings with severity, file/line references, and a verdict (approve / approve with warnings / needs changes). Multiple models review independently, then findings are synthesized and deduplicated. Use this for PR reviews, code audits, or pre-commit checks.
list_providers
List all configured AI providers and their default models for brainstorming. Includes locally installed agent CLIs (claude, codex, ...) which run on an existing subscription instead of metered API credits.
add_provider
Add a new AI provider for brainstorming. Supports any OpenAI-compatible API, or a locally installed agent CLI (kind='cli') that runs on an existing subscription instead of API credits.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"brainstorm": {
"brainstorm": {
"command": "npx",
"args": [
"-y",
"brainstorm-mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_KEY>",
"GEMINI_API_KEY": "<YOUR_KEY>",
"DEEPSEEK_API_KEY": "<YOUR_KEY>"
}
}
}
}
}McpServers
{
"brainstorm": {
"command": "npx",
"args": [
"-y",
"brainstorm-mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_KEY>",
"GEMINI_API_KEY": "<YOUR_KEY>",
"DEEPSEEK_API_KEY": "<YOUR_KEY>"
}
}
}Example 3: Hosted Mode Brainstorm (No API Keys)
Prompt:"Brainstorm using opus, sonnet, and haiku about whether we should use GraphQL or REST"
{ "topic": "GraphQL vs REST for our public API", "models": ["opus", "sonnet", "haiku"], "mode": "hosted", "rounds": 2, "style": "redteam" }
Output:The tool returns prompts for each model. The host (Claude Code) spawns sub-agents with different models, collects responses, and feeds them back viabrainstorm_collect. After all rounds, a synthesis model produces a 3-bullet verdict: Recommendation, Key Tradeoffs, Strongest Disagreement.
Error handling:Sessions expire after 10 minutes. If a session is not found, a clear error message is returned with instructions to start a new one.
- You ask Claude to brainstorm a topic
- The tool sends the topic to all configured providers in parallel — HTTP for API providers, a spawned subprocess for CLI providers
- Claude reads their responses and contributes its own perspective
- Models see each other's responses and refine across rounds
- A synthesizer produces the final verdict
- You ask Claude to brainstorm with specific models (e.g., opus, sonnet, haiku)
- The tool returns prompts — no API calls are made
- Claude spawns sub-agents with different models to execute prompts
- Responses are collected and fed back for the next round
- Repeat until synthesis
brainstorm-mcp runs entirely on your machine and doesnotcollect, store, or transmit any personal data, telemetry, or analytics.
InAPI mode, prompts are sent directly from your machine to the model providers you configure (OpenAI, Gemini, DeepSeek, etc.) using your own API keys. InCLI mode, prompts are passed to agent CLIs installed on your machine, which talk to their own vendors under your existing subscription. Inhosted mode, no external API calls are made.
Debate sessions are stored in-memory only with a 10-minute TTL. No data is written to disk unless you explicitly save results.
- Issues:https://github.com/spranab/brainstorm-mcp/issues
- Email:developer@pranab.co.in
- Repository:https://github.com/spranab/brainstorm-mcp
git clone https://github.com/spranab/brainstorm-mcp.git cd brainstorm-mcp npm install npm run build npm start
Other agent infrastructure by the same author, built to be used together:
- saga-mcp— SQLite-backed project tracker: once the debate settles, the decision goes somewhere durable.
- yantrikdb-mcp— persistent cognitive memory so the agent remembers what you decided and why.
- swarmcode— real-time channel between Claude Code instances on different machines.
- truenas-mcp— 278 TrueNAS SCALE actions behind one hierarchical tool.
- mcpier— self-hosted MCP control plane that keeps API keys off your clients.
Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.
Create AI-moderated interviews and surveys via MCP and share survey links with participants instantly.
Give your AI assistant the ability to identify cognitive blind spots. The official Model Context Protocol (MCP) server for cognitivebiaslabs.com.
A cognitive framework selector to help choose the right mental models and thinking frameworks for any situation.
An MCP server for advanced cognitive analysis, creative problem-solving, and structured thinking using the UCPF framework.
Local-first cross-agent memory MCP. 6-layer structured brain (goal/context/emotion/impl/caveat/learning) with token-saving file diff cache (86% measured savings on re-reads)
An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom.
A private, local research "second brain" for Claude — cited answers from your own library (it won't invent what it can't find), persistent project memory, daily briefs, a live meeting assistant, and 34 specialist agents. Runs entirely on your machine.
Queries multiple Ollama models to combine their responses, offering diverse AI perspectives on a single question.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
