What it does
The server exposes 18 tools for verifying, scoring and attesting AI agents. verify_agent runs a full six-signal trust check, compare_agents compares two agents side by side, and batch_verify checks up to ten agents at once. get_score returns a quick cached score, and attest_agent scores an agent and writes an on-chain EAS attestation. Other tools look up attestations, on-chain identity and reputation signals, check the scam database, report malicious wallets, explain scores and list scoring signals with their weights.
It suits anyone who needs to check whether an agent or wallet is trustworthy before interacting with it, screen wallets against the scam database, or record a verified agent's score on-chain. It is used from Claude, Cursor or another MCP-compatible client, where requests are made in plain language.
It is set up in an MCP client configuration and can run through npx. It is a thin client that calls the public AgentRadar API, whose base URL can be changed through an environment variable. The source is MIT-licensed and available in the repository.
Limitations and requirements
Some calls are paid per use through x402: verify_agent costs $0.005 per call and attest_agent $5.00 per attestation. An operator key removes these charges. Admin endpoints require an operator key. Attestations are written on-chain.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.Bichev/agentradar
Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.
v0.1.3As shown on registry.modelcontextprotocol.io when we last read it