Scan MCP server manifests for tool poisoning, shadowing, hidden unicode injection, and rug pull patterns. Returns JWS-signed ACT/HALT receipt per draft-krausz-verification-state-01.
# 1. Ask the endpoint what it costs (no payment, no wallet needed): curl -i -X GET 'https://agenttrust.uk/v1/scan/mcp' # -> HTTP/1.1 402 Payment Required # the response carries the price, asset and pay-to address. # 2. Pay and retry with any x402 client: npx x402-fetch 'https://agenttrust.uk/v1/scan/mcp'
Endpoint: https://agenttrust.uk/v1/scan/mcp. Operated by agenttrust.uk, not by Animica. Price and availability were correct at the last probe on 2026-09-02 and are set by the operator, who may change them.
Scan any AI agent skill file for malware, prompt injection, data exfiltration, and 40 other threat patterns. Returns risk score 0-100 and JWS-signed ACT/HALT re…