Agent-Safety API

Before an AI agent logs in, pays, or uploads, it should ask Trustiry if the destination is safe:

curl "https://trustiry.com/api/agent/check?url=amaz0n-secure-login.com&action=payment"

Response includes safe_to_proceed, blocked_actions, and the official_alternative. There is also a native MCP server exposing check_url, agent_safety, find_official, and website_trust tools.