Hekkova MCP server

Hekkova MCP Server

The permanent memory layer for AI agents. Connect any MCP-compatible AI (Claude, ChatGPT, Gemini, Cursor, custom agents) and mint moments — photos, videos, audio, text — permanently to the Polygon blockchain with IPFS + Filecoin storage, Lit Protocol encryption, and privacy tiers that let you control who sees what.

Quick Start

# 1. Install dependencies
npm install

# 2. Copy and configure environment variables
cp .env.example .env
# Edit .env with your Supabase, Thirdweb, Pinata, and Stripe credentials

# 3. Seed the local test account and API key
npm run seed

# 4. Start the development server
npm run dev
# → Server running at http://localhost:3000/mcp

Connect with Claude Desktop

Add this to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json Windows: %APPDATA%\Claude\claudedesktopconfig.json

{
  "mcpServers": {
    "hekkova": {
      "type": "url",
      "url": "http://localhost:3000/mcp",
      "headers": {
        "Authorization": "Bearer hk_test_local_dev_key_12345678"
      }
    }
  }
}

For production, replace the URL and API key:

{
  "mcpServers": {
    "hekkova": {
      "type": "url",
      "url": "https://mcp.hekkova.com/mcp",
      "headers": {
        "Authorization": "Bearer hk_live_YOUR_API_KEY"
      }
    }
  }
}

Get your API key at hekkova.com/dashboard/keys.

Tool Reference

Privacy Phases

Moment Categories

Rate Limits

Rate limit headers are included on every response:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 58
X-RateLimit-Reset: 1710680460

Running Tests

# Make sure the server is running in another terminal
npm run dev

# Run the test client
npm run test-client

Deployment

Vercel (Serverless)

npm install -g vercel
vercel

Add a vercel.json:

{
  "builds": [{ "src": "src/server.ts", "use": "@vercel/node" }],
  "routes": [{ "src": "/(.*)", "dest": "src/server.ts" }]
}

Set all environment variables in the Vercel dashboard under Project → Settings → Environment Variables.

Railway

Shortened. The full README is on GitHub.