Crypto safety checks for AI agents on Base: is this token a scam, is this address safe to send to, has this creator rugged before. A new caller's first 2 checks per tool are free. Call the HTTP endpoints listed under skills, paid per call with x402 (USDC on Base) or the MCP server at https://trust-check.gm-tools.workers.dev/mcp. There is no A2A message endpoint.

A2A readiness

D · 49/100

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here C+, 86.9/100), which weighs availability, conformance, card completeness and speed. How the two differ

Valid Agent Card	10/10	Parseable Agent Card with the required fields.
Live JSON-RPC	0/25	Endpoint did not answer (669 ms).
Protocol version	5/10	Declares pre-1.0 A2A 0.3.0. Upgrade to v1.x for full points.
JWS signature	0/10	Card is unsigned.
Uptime (30 days)	15/15	3/3 probes succeeded; final after 5 probes in 30 days.
Skill declaration	10/10	Declares 5 skill(s) with structured metadata.
Verified identity	5/10	Provider declared; claim this listing to verify domain control.
Freshness + modern flags	4/5	seen in a source within 7 days.
Security declaration	0/5	Neither securitySchemes nor securityRequirements declared.

Responsiveness: Responsive (669 ms; bands ≤2.5 s, ≤5 s, ≤8 s, slower; penalty only).

Measured 2026-11-11.

Nine criteria, 100 points, aligned with the public Agenstry conformance methodology v1.1. Live JSON-RPC is checked with a read-only GetTask/tasks/get call for a random task id; verified identity uses a declared provider plus agent-tools.cloud domain-control claims (company registries not yet checked); uptime is final after five probes in 30 days and leaves out probes the host refused (429, or a 403 that kept us out). Grades: A>=90, B>=75, C>=60, D>=40, F<40. Display only: search order uses the quality grade.

Compared with peers

Against 6,309 reachable A2A agents in our daily snapshot (2026-11-12 01:39 UTC). Display only; it does not change search order.

Readiness: Higher than 40% of peers; This listing 49 · peer median 54
Latency: Faster than 7% of peers; This listing 1,074 ms · peer median 398 ms

Where it loses the most points, and how to win them back

Live JSON-RPC −25 — Answer JSON-RPC at the URL the Agent Card declares.
Now: Endpoint did not answer (669 ms).
JWS signature −10 — Sign the Agent Card (JWS).
Now: Card is unsigned.
Protocol version −5 — Support the current protocol revision.
Now: Declares pre-1.0 A2A 0.3.0. Upgrade to v1.x for full points.

How many agent tools actually work · All statistics

Skills

Token safety check

Is this token safe to buy? Honeypot and tax simulation, owner powers, whales, liquidity, scam lists. $0.002 per check. Call: GET /v1/token?address=<token>

cryptosecurityhoneypotscamtokenbaseaddress-poisoningwallettoken
Address safety check

Is this address safe to send to? Scam lists, address poisoning, token contracts, burn addresses. $0.002 per check. Call: GET /v1/address?address=<to>&from=<your wallet>

cryptosecurityhoneypotscamtokenbaseaddress-poisoningwalletaddress
Rug Watch feed

Recent liquidity collapses on Base (rug pulls and dumps) with creator wallets. $0.002 per call. Call: GET /v1/rugs?hours=24

cryptosecurityhoneypotscamtokenbaseaddress-poisoningwalletrug-pull
Creator record

Has this token creator rugged before? $0.002 per check. Call: GET /v1/creator?address=<deployer>

cryptosecurityhoneypotscamtokenbaseaddress-poisoningwalletcreator
Deep Safety Report

Token check plus creator record, funder, owner, liquidity history, website age, AI summary and what to do. $0.10 per report, no free tier. Call: GET /v1/report?address=<token>

cryptosecurityhoneypotscamtokenbaseaddress-poisoningwalletreport

How to call

A2A endpoint (HTTP+JSON)

https://trust-check.gm-tools.workers.dev/

Agent card

https://trust-check.gm-tools.workers.dev/.well-known/agent-card.json

Documentation

https://trust-check.gm-tools.workers.dev/llms.txt

Homepage

https://gntech.gm-tools.workers.dev

Listed in

Directories this entry was found in.

agenstry since 2026-11-08