#agent-trust

AgentRank is the settlement-grounded trust check for AI agents. Before your agent pays, hires, or extends credit to another agent or x402 service, call check_agent_trust to see if it is real and settlement-backed: a 0-1000 reputation score computed from real on-chain USDC settlement (sybil-resistant, continuously stress-tested against collusion). Also: gate_caller (gate your own service by a caller's rank), classify_x402_address (real service vs rail vs treasury vs dust), and state_of_x402 (the de-noised census of the whole x402 economy). 78% of x402 counterparties are unverifiable ghosts; AgentRank tells you which are real. Free, read-only, no API key. By Crest Deployment Systems.

86 self-hosted MCP servers with 989 tools across 7 categories. Complete Agent Trust Runtime: identity (KYA), policy enforcement (258 rules), fraud detection (DetectiveOracle), self-healing support (SupportOracle), and signed Trust Passports. x402 USDC micropayments. Built for autonomous AI agents.

The first DORA Operating System for regulated financial entities. 50 MCP tools covering all 26 DORA articles, MiCA stablecoin compliance, AML screening (87k sanctions names), macro intelligence (86 FRED series), and a complete Agent Trust Runtime — identity (KYA), policy enforcement (258 rules), fraud detection (DetectiveOracle), self-healing support (SupportOracle), and signed Trust Passports. Every response ES256K-signed and blockchain-anchored (Polygon + XRPL). Free tier available (100 calls/day). Built for AI agents that need to act compliantly in regulated markets.