80trust / 100

Safety Product

by safety-product in Security & trust

x402 APIPassing, checked 6 min ago

Product recall and safety check for a consumer good, food, drug or medical device by brand or product name. Fuses CPSC and openFDA recalls into one cited JSON with hazard, FDA class, remedy, status and a deterministic risk score. Risk indicators, not advice.

GET https://api.agentstools.dev/safety/product

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
75 ms typical, 118 ms slowest 5%
Last check
6 min ago
Next check
in 25 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X GET "https://api.agentstools.dev/safety/product?domain=all&query=Fisher-Price+stroller"
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fapi.agentstools.dev%2Fsafety%2Fproduct
const res = await pay("https://api.agentstools.dev/safety/product?domain=all&query=Fisher-Price+stroller");
console.log(await res.json());

Example input

{
  "domain": "all",
  "query": "Fisher-Price stroller"
}

Example output

{
  "matched_count": 3,
  "matched_recalls": [
    {
      "classification": "Class I",
      "date": "2022-05-20",
      "hazard": "Salmonella contamination",
      "match_score": 100,
      "source": "openfda_food",
      "status": "terminated"
    }
  ],
  "query": {
    "domain": "all",
    "query": "peanut butter"
  },
  "risk_score": {
    "band": "high",
    "flags": {
      "max_fda_classification": "Class I"
    },
    "score": 57
  },
  "sources": {
    "partial": false
  }
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
6 min agoPassed402118 ms$0.02
4 h agoPassed40285 ms$0.02
8 h agoPassed40275 ms$0.02
11 h agoPassed40223 ms$0.02
15 h agoPassed402148 ms$0.02
19 h agoPassed40277 ms$0.02
22 h agoPassed40223 ms$0.02
27 h agoPassed40221 ms$0.02