Credit-score-style TEASER for one ERC-8004 agent's trust profile.

Args (BOTH OPTIONAL — call with {} to see Agent Zero itself): chain: one of "base", "ethereum". Default: "base". agent_id: the numeric ERC-8004 agent id. Default: 19353 (Agent Zero, the agent serving this MCP endpoint). Example: {} returns Agent Zero on base; {"chain": "base", "agent_id": 19353} is the explicit form.

By construction returns ONLY: name, chain, agent_id, public readiness_bucket, and a 1-line verdict headline. Every decision-driving value — trust_verdict, readiness_score, risk_flags, money-flow details, counterparty list, full score breakdown — is redacted as null and enumerated in the locked map. The response carries the exact paid endpoint URL (/v1/intel/agent/{agent_id}?chain={chain}), the x402 price as currently configured, and a one-line how-to-pay-via-x402 hint. Returns error with the same unlock pointer if the agent is not indexed, so a caller probing an unknown id still sees how to pay for a known one.

Paid counterpart: GET /v1/intel/agent/{agent_id}?chain={chain} (x402, USDC on base-mainnet) returns the full trust verdict (safe_to_transact / caution / avoid / insufficient_data), readiness_score + sub-scores, Sybil-adjusted reputation, and the commerce-backed money-flow breakdown. Every response from this free tool carries an unlock + paid_upgrade block with the exact paid endpoint, price, and payment discovery.