@craftedtrust/mcp-config

Add CraftedTrust trust verification to your AI agent. One line of config and your agent checks every MCP server before connecting.

Quick Start

Add to your agent's MCP config (Claude Desktop, Cursor, Windsurf, or any MCP client):

{
  "mcpServers": {
    "craftedtrust": {
      "url": "https://mcp.craftedtrust.com/api/v1/mcp",
      "description": "Check trust scores before connecting to MCP servers"
    }
  }
}

Programmatic Usage

import { mcpConfig, isSafe, CRAFTEDTRUST_URL } from '@craftedtrust/mcp-config';

// Get the MCP config object
console.log(mcpConfig);

// Check if a grade is safe (default minimum: C)
isSafe('B');  // true
isSafe('F');  // false
isSafe('D', 'D');  // true (custom threshold)

Available Tools

| Tool | Price | Description | |---|---|---| | check_trust | $0.005 | Look up trust score by URL or npm name | | scan_server | $0.25 | Trigger a live security scan | | search_registry | Free | Search 4,200+ indexed MCP servers | | get_stats | Free | Ecosystem statistics | | pay_for_certification | Free | Initiate USDC certification payment | | verify_payment | Free | Verify on-chain USDC payment |

Prices are via x402 (USDC on Base). Free with API key.

Trust-Gated Connection Pattern

result = call_tool("craftedtrust", "check_trust", {"server_url": "https://mcp.example.com"})

if result["grade"] in ("D", "F"):
    return f"Refused: scored {result['grade']} ({result['score']}/100)"

connect_to_server("https://mcp.example.com")

Full examples: trust-gated-agent-example

Links

• API Docs
• Interactive API Reference
• OpenAPI Spec
• Security Standards

License

MIT - Cyber Craft Solutions LLC