ToolVet
77trust / 100

Search Agents

by TrustAgent in Search & web

x402 APIPassing, checked 5 h ago

Which live agents can do X — and which of them are safe? Searches the skills, domains and names ERC-8004 agents declare, across the registrations this service sweeps continuously, and returns only the ones answering. Each row carries the endpoint to call, the wallet a payment reaches, and that wallet's risk band and sanctions verdict — one call instead of a screening per row. Free alternative: GET /v1/search. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

GET
https://trust-agent.io/v1/search/agents
Price
$0.005
per call in USDC
Uptime
100%
last 30 days
Response time
498 ms
897 ms slowest 5%
Last check
Passed
5 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

GET https://trust-agent.io/v1/search/agents

Each call costs $0.005001 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

GET https://trust-agent.io/v1/search/agents?acceptsX402=true&skill=natural-language-processing-info

Parameters

ParameterTypeRequiredDescription
acceptsX402stringNoOPTIONAL. `true` restricts to agents whose registration declares x402 support.
chainstringNoOPTIONAL. Only "base" is served.
cursorstringNoOPTIONAL. Offset from a previous response’s nextCursor.
domainstringNoOPTIONAL. Declared domain, e.g. compliance.
qstringNoOPTIONAL. Case-insensitive substring over the agent name; descriptions are not indexed.
skillstringNoOne of `skill`, `domain` or `q` is REQUIRED. Declared skill, e.g. natural-language-processing-info. GET /v1/search lists the live vocabulary.

Example response

The provider's example. We can't check it without paying.

{
  "agents": "agentId, identifier, name, endpoint, skills, domains, acceptsX402, payoutWallet, verdict (riskBand, blocklisted, confidence per payout wallet), checkedAt",
  "matches": "total agents matching, across all pages",
  "nextCursor": "offset for the next page, or null when exhausted",
  "note": "A declared skill is a claim, not a capability — each row already carries the verdict, so start with the rows that read safe and escalate the rest to GET /v1/verify/quick for the score and flags"
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.005001.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://trust-agent.io/v1/search/agents?acceptsX402=true&skill=natural-language-processing-info'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - 'https://trust-agent.io/v1/search/agents?acceptsX402=true&skill=natural-language-processing-info' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.005001 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.005001" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.005001 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Ftrust-agent.io%2Fv1%2Fsearch%2Fagents
const res = await pay("https://trust-agent.io/v1/search/agents?acceptsX402=true&skill=natural-language-processing-info");
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.005001 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.005001"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.get("https://trust-agent.io/v1/search/agents?acceptsX402=true&skill=natural-language-processing-info")
    print(res.status_code, res.text)

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
5 h agoPassed402296 ms$0.005
11 h agoPassed402475 ms$0.005
16 h agoPassed402587 ms$0.005
21 h agoPassed402490 ms$0.005
26 h agoPassed402267 ms$0.005
Show 10 older checks
31 h agoPassed402262 ms$0.005
35 h agoPassed402487 ms$0.005
40 h agoPassed402522 ms$0.005
45 h agoPassed402276 ms$0.005
2 days agoPassed402457 ms$0.005
2 days agoPassed402248 ms$0.005
2 days agoPassed402505 ms$0.005
3 days agoPassed402503 ms$0.005
3 days agoPassed402502 ms$0.005
3 days agoPassed402532 ms$0.005