Wraps the AgentRadar API to bring trust scoring and scam detection for blockchain agents into Claude or Cursor. You get 18 tools covering verification (six signal checks per agent), batch scoring, side-by-side comparisons, and EAS attestation writes on Base. The verify_agent tool runs full trust checks, attest_agent writes on-chain attestations for ERC-8004 agents, and check_scam queries their scam database. Most reads are free, verification costs $0.005 via x402 micropayments, attestations run $5 unless you supply an operator key. Useful if you're building or auditing AI agents on Base and want trust data without leaving your editor.
MCP 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.
io.github.Bichev/agentradarThis 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.
| Tool | Description |
|---|---|
verify_agent | Full 6-signal trust verification |
compare_agents | Side-by-side comparison of two agents |
batch_verify | Verify up to 10 agents at once |
get_score | Quick cached trust score lookup |
get_badge_url | Generate embeddable trust badge URL |
attest_agent | Score + write on-chain EAS attestation |
get_attestations | List all attestations |
get_attestation_by_tx | Look up attestation by tx hash |
lookup_identity | On-chain identity (ERC-8004) |
lookup_reputation | Reputation signals |
resolve_agent_uri | Resolve agent URI/metadata |
check_scam | Check scam database |
add_scam_wallet | Report malicious wallet |
explain_score | Human-readable score explanation |
get_health | API health check |
get_stats | Dashboard statistics |
list_signals | List scoring signals + weights |
get_pricing | API pricing info |
Add to your project's .cursor/mcp.json:
{
"mcpServers": {
"agentradar": {
"command": "npx",
"args": ["-y", "@agentradar/mcp"],
"env": {
"AGENTRADAR_OPERATOR_KEY": "your-key-here"
}
}
}
}
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"agentradar": {
"command": "npx",
"args": ["-y", "@agentradar/mcp"],
"env": {
"AGENTRADAR_OPERATOR_KEY": "your-key-here"
}
}
}
}
npx @agentradar/mcp
git clone https://github.com/Bichev/agentradar-mcp.git
cd agentradar-mcp
npm install
npm run build
node dist/index.js
| Variable | Required | Default | Description |
|---|---|---|---|
AGENTRADAR_API_URL | No | https://api.vvpro.ai | API base URL |
AGENTRADAR_OPERATOR_KEY | No | — | Operator key for admin endpoints and bypassing x402 payment |
Once connected, you can ask your AI assistant:
MIT
AGENTRADAR_API_URLAgentRadar API base URL. Defaults to https://api.vvpro.ai (production, Base mainnet).
AGENTRADAR_OPERATOR_KEYsecretOperator key for admin endpoints and bypassing x402 payment. Optional — leave empty for public, x402-paid usage.