{
  "markdown": "# @agentradar/mcp\n\n[![npm version](https://img.shields.io/npm/v/@agentradar/mcp.svg)](https://www.npmjs.com/package/@agentradar/mcp)\n[![Build](https://github.com/Bichev/agentradar-mcp/actions/workflows/build.yml/badge.svg)](https://github.com/Bichev/agentradar-mcp/actions/workflows/build.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-io.github.Bichev%2Fagentradar-orange)](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.Bichev/agentradar)\n\nMCP Server for **AgentRadar** — the on-chain trust oracle for the agent economy. Provides 18 tools for verifying, scoring, and attesting AI agent trustworthiness directly from Claude, Cursor, or any MCP-compatible client.\n\n- **Live API:** https://api.vvpro.ai\n- **Web:** https://vvpro.ai\n- **MCP Registry:** [`io.github.Bichev/agentradar`](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.Bichev/agentradar)\n\nThis package is a thin client wrapper around the public AgentRadar API. The full source is auditable here — anything `npx @agentradar/mcp` runs is in this repo, MIT-licensed.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `verify_agent` | Full 6-signal trust verification |\n| `compare_agents` | Side-by-side comparison of two agents |\n| `batch_verify` | Verify up to 10 agents at once |\n| `get_score` | Quick cached trust score lookup |\n| `get_badge_url` | Generate embeddable trust badge URL |\n| `attest_agent` | Score + write on-chain EAS attestation |\n| `get_attestations` | List all attestations |\n| `get_attestation_by_tx` | Look up attestation by tx hash |\n| `lookup_identity` | On-chain identity (ERC-8004) |\n| `lookup_reputation` | Reputation signals |\n| `resolve_agent_uri` | Resolve agent URI/metadata |\n| `check_scam` | Check scam database |\n| `add_scam_wallet` | Report malicious wallet |\n| `explain_score` | Human-readable score explanation |\n| `get_health` | API health check |\n| `get_stats` | Dashboard statistics |\n| `list_signals` | List scoring signals + weights |\n| `get_pricing` | API pricing info |\n\n## Installation\n\n### Cursor\n\nAdd to your project's `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agentradar\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@agentradar/mcp\"],\n      \"env\": {\n        \"AGENTRADAR_OPERATOR_KEY\": \"your-key-here\"\n      }\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"agentradar\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@agentradar/mcp\"],\n      \"env\": {\n        \"AGENTRADAR_OPERATOR_KEY\": \"your-key-here\"\n      }\n    }\n  }\n}\n```\n\n### npx (direct)\n\n```bash\nnpx @agentradar/mcp\n```\n\n### Local development\n\n```bash\ngit clone https://github.com/Bichev/agentradar-mcp.git\ncd agentradar-mcp\nnpm install\nnpm run build\nnode dist/index.js\n```\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|----------|----------|---------|-------------|\n| `AGENTRADAR_API_URL` | No | `https://api.vvpro.ai` | API base URL |\n| `AGENTRADAR_OPERATOR_KEY` | No | — | Operator key for admin endpoints and bypassing x402 payment |\n\n## Usage Examples\n\nOnce connected, you can ask your AI assistant:\n\n- \"Verify this agent: 0x742d35Cc6634C0532925a3b844Bc9e7595f2bD28\"\n- \"Is 0xdead...beef a known scam wallet?\"\n- \"Compare these two agents and tell me which is more trustworthy\"\n- \"Explain why this agent scored 45/100\"\n- \"Write an on-chain attestation for this verified agent\"\n\n## Pricing\n\n- **verify_agent**: $0.005 per call (x402) or free with operator key\n- **attest_agent**: $5.00 per attestation (x402) or free with operator key\n- **get_score**: Free\n- **Admin endpoints**: Operator key required\n\n## License\n\nMIT\n",
  "bytes": 3850,
  "sha": "24ae1bc6c7af0e4f3d29db9d86395efcf85d0262ecdd6a8356a07edaa98500c6",
  "repo_slug": "bichev/agentradar-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_bichev_agentradar_d1cae977/readme"
}