hivemind
Instant troubleshooting solutions for AI coding assistants Community-driven knowledge base with 16,000+ solutions and growing
Works with any MCP-compatible CLI: Claude Code, Codex CLI, Gemini CLI, Grok CLI, Cursor, and more.
🎯 What is hivemind?
hivemind is a Model Context Protocol (MCP) server that gives AI coding assistants instant access to a searchable knowledge base of troubleshooting solutions.
Supported platforms:
- Claude Code (Anthropic)
- Codex CLI (OpenAI)
- Gemini CLI (Google)
- Grok CLI (xAI)
- Cursor
- Any MCP-compatible tool
When you hit an error, search hivemind - get ranked solutions from the community in seconds.
✨ Features
- 🔍 Full-text search - Fast Postgres FTS with relevance ranking
- 👍 Community feedback - Say "hivemind: worked" to rate solutions
- 🎯 Trigger words - AI automatically tracks your feedback
- 📊 Smart ranking - Solutions sorted by success rate and votes
- 🚀 Zero config - No API keys, no setup, just install and use
- ⚡ Fast - < 1s search response time
📦 Installation
Quick Install
Claude Code:
npm install -g hivemind-mcp
claude mcp add hivemind -- npx hivemind-mcp
Codex CLI:
npm install -g hivemind-mcp
codex mcp add hivemind -- npx -y hivemind-mcp
Gemini CLI:
npm install -g hivemind-mcp
gemini mcp add hivemind npx -y hivemind-mcp
Cursor / Windsurf:
npm install -g hivemind-mcp
# Add to MCP settings: npx hivemind-mcp
Manual Setup (Claude Code)
Option A: Via Claude Code UI
- Open Claude Code settings
- Go to MCP Servers section
- Add new server:
- Name:
hivemind - Command:
npx - Args:
["hivemind-mcp"]
- Name:
Option B: Via config file
Edit ~/.config/claude/mcp_config.json:
{
"mcpServers": {
"hivemind": {
"command": "npx",
"args": ["hivemind-mcp"]
}
}
}
Restart your CLI/editor to activate the MCP server.
🚀 Usage
Search for Solutions
User: "MCP connection refused"
AI: [searches hivemind automatically]
Or explicitly:
User: "Search hivemind for playwright timeout"
Give Feedback
After trying a solution:
User: "hivemind: worked"
Or:
User: "hivemind: failed"
Your AI automatically tracks your feedback to improve rankings!
📚 Example Queries
| Problem | Query |
|---|---|
| MCP won't connect | "MCP connection refused" |
| Playwright issues | "playwright click not working" |
| Claude hooks | "hooks don't fire" |
| Auth problems | "user signed in but gets must sign in error" |
| Supabase issues | "supabase migration failed" |
Current knowledge base: 16,000+ solutions (and growing) covering MCP, Playwright, Supabase, web development, databases, security, and more.
🤝 Contributing Solutions
Have a solution that helped you? Share it with the community!
Via MCP Tool
User: "I want to contribute a solution"
Claude: [guides you through contribution form]
Via Email
Send to: [your-email] (Beta testers will get this in welcome message)
Include:
- Problem/error message
- Category (mcp-troubleshooting, web-automation, etc.)
- Step-by-step solutions
- What to check before/after
- Common mistakes
🎓 How Trigger Words Work
When you say "hivemind: worked" or "hivemind: failed":
- Your AI recognizes the trigger phrase
- Automatically calls feedback tool
- Backend increments thumbs_up or thumbs_down
- Future searches show better-ranked solutions
Why trigger words? Natural language ("that worked") is ambiguous. Trigger phrases ensure your AI ALWAYS catches your feedback.
🛡️ Infrastructure
Rate Limits:
- Search: 100 requests/hour per IP
- Voting: 20 votes/hour per IP
- Contributions: 5/hour per IP
Stack:
- Backend: Supabase (Postgres 17 + Edge Functions)
- Database: 16,000+ solutions
- Security: IP banning, input sanitization, moderated contributions
🔒 Security
hivemind is designed to be a safe, public knowledge base. We take security seriously:
Credential Scanning
All contributions are scanned for sensitive data before storage. Our scanner blocks:
- API Keys: OpenAI, Anthropic, AWS, GCP, Azure, Stripe, Slack, GitHub, GitLab, and 30+ providers
- Tokens: JWT, Bearer tokens, OAuth tokens, PATs
- Secrets: Database passwords, webhook URLs, Basic auth headers
- Obfuscation Attempts: Base64-encoded secrets, zero-width character tricks
How it works:
- Pattern matching against 45+ known secret formats
- Base64 decode + rescan for hidden secrets
- Entropy analysis for high-randomness strings near keywords like
key=,secret= - Zero-width character stripping to defeat obfuscation
If your contribution is rejected, check for accidentally included credentials.
Row-Level Security
All database tables use Postgres RLS policies. The public API can only:
- Read solutions and skills
- Submit contributions (to moderation queue)
- Submit feedback votes
No direct write access to production data.
Rate Limiting
Aggressive rate limits prevent abuse:
- Search: 100/hour
- Voting: 20/hour
- Contributions: 5/hour
What We Don't Store
- No user accounts required
- No tracking cookies
- No personally identifiable information
- IP addresses used only for rate limiting (not logged with searches)
See PRIVACY.md for full privacy policy.
📊 Monitoring
Beta testers: We monitor usage via Supabase dashboard. You can check your own usage:
# View your recent searches (if you clone the repo)
source ~/.claude/scripts/turso-helpers.sh
db-stats
See MONITORING.md for admin dashboard access.
🗺️ Roadmap
Completed:
- ✅ Core search and feedback
- ✅ Trigger word system
- ✅ Rate limiting
- ✅ Security (IP bans, sanitization, moderation queue)
- ✅ 16,000+ solutions
- ✅ Version update notifications
Coming Soon:
- Semantic search (AI embeddings)
- Contributor leaderboard
- Browser extension
- Dangerous command blocklist
See ROADMAP.md for full details.
🔧 Technical Details
Stack:
- MCP Server: TypeScript + @modelcontextprotocol/sdk
- Backend: Supabase (Postgres 17 + Deno Edge Functions)
- Search: Postgres Full-Text Search (ts_rank)
- Hosting: Supabase free tier + npm registry
Architecture:
User → Any AI CLI/Editor → MCP → Supabase Edge Functions → Postgres
Public Source:
hivemind-mcp/- MCP client package (what you install via npm)
📄 Documentation
- INSTALL.md - Detailed installation guide
- TRIGGER_FEEDBACK_SYSTEM.md - How feedback works
- MONITORING.md - Admin monitoring guide
- ROADMAP.md - Product roadmap
❓ Troubleshooting
MCP not loading
# Check if installed
npm list -g hivemind-mcp
# Reinstall
npm install -g hivemind-mcp@latest
# Restart your AI CLI/editor
Search not working
- Check your AI CLI MCP logs
- Verify internet connection
- Try: "Search hivemind for test"
Feedback not tracked
Known issue - tracking endpoint works but MCP may not call it consistently. We're debugging this.
🐛 Reporting Issues
- Check existing issues
- Create new issue with:
- What you tried
- What happened
- Your AI CLI (Claude Code, Codex, Gemini, etc.)
- Operating system
📜 License
MIT License - see LICENSE file
🌟 Star History
If hivemind helped you, give it a star ⭐
Built with ❤️ for the AI coding community