Rug Munch Intelligence — MCP Server

19 tools for crypto token risk intelligence. Detect rug pulls, honeypots, and scams before your agent transacts.

Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.

What It Does

Quick Start

Install

pip install rug-munch-mcp

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "rug-munch": {
      "command": "rug-munch-mcp",
      "env": {}
    }
  }
}

Cursor / Windsurf

Add to your MCP config:

{
  "rug-munch": {
    "command": "python3",
    "args": ["-m", "rug_munch_mcp"]
  }
}

From Source

git clone https://github.com/CryptoRugMunch/rug-munch-mcp
cd rug-munch-mcp
pip install -e .
rug-munch-mcp

Payment

Endpoints are paid via x402 USDC micropayments on Base mainnet. When you call a paid tool, the API returns HTTP 402 with payment details. x402-compatible clients handle this automatically.

Alternatively, set an API key to bypass x402:

{
  "mcpServers": {
    "rug-munch": {
      "command": "rug-munch-mcp",
      "env": {
        "RUG_MUNCH_API_KEY": "your-key-here"
      }
    }
  }
}

Supported Chains

Solana, Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche

Architecture

Your Agent (Claude, Cursor, etc.)
    ↓ MCP stdio
rug-munch-mcp (this package)
    ↓ HTTPS
cryptorugmunch.app/api/agent/v1/*
    ↓ x402 payment (if needed)
Rug Munch Intelligence API
    ↓
240K+ scans, 114K+ flagged tokens, AI forensics

Other Integration Methods

• x402 Direct: x402-trading-agent — Example Python agent
• AgentKit Plugin: rug-agent-kit — Coinbase AgentKit integration
• A2A: https://cryptorugmunch.app/.well-known/agent.json
• OpenAPI: https://cryptorugmunch.app/api/agent/v1/openapi.json

Links

• API Status: https://cryptorugmunch.app/api/agent/v1/status
• Discovery: https://cryptorugmunch.app/.well-known/mcp.json
• Docs: https://cryptorugmunch.app/api/agent/v1/skill.md
• GitHub: https://github.com/CryptoRugMunch

License

MIT