No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by spranab · MCP Server · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is brainstorm-mcp safe to install? View the security audit →
brainstorm-mcp An MCP server that runs multi-round brainstorming debates between AI models. Connect it to Claude Code (or any MCP client) and let GPT, Gemini, DeepSeek, Groq, Ollama, and others debate your ideas — with Claude as an active participant in every round. No more single-perspective answers. brainstorm-mcp pits multiple LLMs against each other so you get diverse viewpoints, critiques, and a consolidated synthesis. Features Claude as participant — Claude debates alongside external models, bringing full conversation context Multi-round debates — Models see and critique each other's responses across rounds Parallel execution — All models respond concurrently within each round Per-model timeouts — 2-minute timeout per API call, one slow model won't block others Context truncation — Automatically truncates history when approaching context limits Cost estimation — Shows estimated token usage and cost per debate Resilient — One model failing doesn't abort the debate Synthesizer fallback — If the primary synthesizer fails, tries other models Session management — Interactive sessions with 10-minute TTL, automatic cleanup GPT-5.x / o3 / o4 compatible — Automatically uses for newer...
| Stars | 70 |
| Forks | 8 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 76.2562631721111/100 |
| Last Updated | 2026-09-19 |
| Created | 2026-02-23 |
| Platforms | claude-code, gemini, mcp, node |
| Est. Tokens | ~15k |
Looking for a brainstorm-mcp alternative? If you're comparing brainstorm-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman coll
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and u
📜 An MCP server for conversation history search and retrieval in Claude Code
c4 GenAI Suite
Explore other popular mcp server tools:
brainstorm-mcp is A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as a. It is categorized as a MCP Server with 70 GitHub stars.
brainstorm-mcp is primarily written in TypeScript. It covers topics such as ai, ai-agents, ai-debate.
You can find installation instructions and usage details in the brainstorm-mcp GitHub repository at github.com/spranab/brainstorm-mcp. The project has 70 stars and 8 forks, indicating an active community.
brainstorm-mcp is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to brainstorm-mcp on Agent Skills Hub include postman-mcp-server, deep-code-reasoning-mcp, claude-emporium. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: