← all agents · MCP trust index

AgentIAM

Identity, safety & execution proofs for autonomous agents. 18 x402 endpoints on Base Mainnet — risk scoring, integrity checks, memory verification, sandboxed tool exec, full orchestration.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:19:53Z, first seen 2026-08-26T05:54:18Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://achillesalpha.com
card sourcehttps://achillesalpha.onrender.com/.well-known/agent-card.json
protocolVersion0.2.0
agent version1.0.0
preferredTransport
providerAchilles Alpha
skills published10
card hash (canonical)141dfb3f55bddfc1

Interface URLs

transportURL
unspecifiedhttps://achillesalpha.com

Skills (from card)

skilldescription
EP ValidatePolicy validation — deterministic risk + compliance + proof hash for any agent proposal. $0.01 USDC via x402.
Risk CheckQuick risk score by action type / value / leverage. $0.005 USDC via x402.
NoLeakExecution integrity — tamper detection, leak/injection defense. $0.01 USDC via x402.
MemGuardState verification — memory drift & corruption detection. $0.01 USDC via x402.
RiskOraclePre-action multi-factor risk scoring. $0.01 USDC via x402.
SecureExecSandboxed tool execution with proof hash. $0.01 USDC via x402.
FlowCoreFull orchestration pipeline — chains NoLeak + RiskOracle + SecureExec + MemGuard in one call. $0.02 USDC via x402.
Code AuditOWASP-class vulnerability detection. $0.03 USDC via x402.
Research BriefStructured intel brief — web research + analysis. $0.05 USDC via x402.
DELPHI SignalsReal-time intel signals (crypto, AI, DeFi, macro) + knowledge graph. $0.001–$0.01 USDC via x402.

Card-drift history

Watching this agent since 2026-08-26T05:54:18Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpointgradeMCP OKauth
https://achillesalpha.onrender.com/mcpD?

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.