← all agents · MCP trust index

AgentRisk

Pre-trade risk scoring for Base tokens. Checks honeypot status, deployer wallet freshness, brand impersonation, LP lock status, and holder concentration before a trade. Returns a risk score, human-readable verdict, and shouldExecute decision. Paid per call via x402, no signup, no API keys.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:14:56Z, first seen 2026-08-26T20:53:14Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://agentrisk.dev/scan
card sourcehttps://agentrisk.dev/.well-known/agent.json
protocolVersion0.3
agent version1.0.0
preferredTransport
providerAgentRisk
skills published1
card hash (canonical)cc961a08b8a8242a

Interface URLs

transportURL
unspecifiedhttps://agentrisk.dev/scan

Skills (from card)

skilldescription
Base Token Risk CheckChecks whether a Base token is safe to trade: honeypot detection, ownership/pausability, LP lock status cross-checked on-chain, holder concentration, deployer wallet freshness, and brand impersonation

Card-drift history

Watching this agent since 2026-08-26T20:53:14Z. 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.

when (UTC)whatversionskillshash washash now
2026-08-29T00:22:19Zchanged?→1.0.00→1f727adff54cc961a08b8

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://agentrisk.dev/mcp/manifestAopen

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.