75trust / 100

Calc Hat

by magent in Other

x402 APIPassing, checked 6 h ago

HAT (Lou 2008 Neurology) for sICH after stroke thrombolysis. Diabetes or glucose >200 mg/dL (1; not additive). NIHSS <15 0, 15-20 1, >20 2. CT hypodensity none 0, <1/3 MCA 1, >1/3 MCA 2 (no equals-1/3). Max 5. Collective sICH 2/5/10/15/44% for scores 0/1/2/3/>3. Glucose in mg/dL (mmol × 18). Not a tPA withhold. magent does not assign NIHSS or read CT.

GET
https://api.magentlab.com/api/calc/hat
Price
$0.005
per call in USDC
Uptime
100%
last 30 days
Response time
225 ms
350 ms slowest 5%
Last check
Passed
6 h ago, next in 8 min

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://api.magentlab.com/api/calc/hat

Each call costs $0.005 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://api.magentlab.com/api/calc/hat?diabetes=false&glucose_mg_dl=108&glucose_mmol_l=6&hypodensity=none&nihss=10

Parameters

ParameterTypeRequiredDescription
diabetesbooleanYesHistory of diabetes mellitus (Lou 2008). true scores 1 on the diabetes-or-glucose item; not additive with glucose >200 mg/dL.
glucose_mg_dlnumberNoBaseline glucose in mg/dL (50-1000). Provide this or glucose_mmol_l, not both. >200 scores 1 on the diabetes-or-glucose item if diabetes is false; 200.0 does not (Lou 2008).
glucose_mmol_lnumberNoBaseline glucose in mmol/L (2.8-55.5). Provide this or glucose_mg_dl, not both. Converted as mg/dL = mmol/L × 18. Scores 1 on the diabetes-or-glucose item if >200 mg/dL after conversion (200.0 does not).
hypodensitystringYesEasily visible hypodensity on initial CT as assigned by the caller (Lou 2008). none scores 0; less_than_third (<1/3 MCA) scores 1; greater_than_third (>1/3 MCA) scores 2. No published equals-1/3 category. magent does not read the CT. One of: none, less_than_third, greater_than_third.
nihssintegerYesCaller-assigned pretreatment NIH Stroke Scale total (integer 0-42). <15 scores 0; 15-20 scores 1; >20 scores 2 (Lou 2008). magent does not compute NIHSS or examine the patient.

Example response

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

Example response, 41 lines
{
  "citation": {
    "authors": "Lou M, Safdar A, Mehdiratta M, Kumar S, Schlaug G, Caplan L, Searls D, Selim M",
    "doi": "10.1212/01.wnl.0000330297.58334.dd",
    "id": "lou-2008",
    "pmid": "18955684",
    "source": "Neurology. 2008;71(18):1417-1423",
    "title": "The HAT Score: a simple grading scale for predicting hemorrhage after thrombolysis"
  },
  "components": [
    {
      "diabetes": false,
      "factor": "diabetes_or_glucose",
      "points": 0,
      "present": false,
      "value": 108
    },
    {
      "factor": "nihss",
      "points": 0,
      "present": false,
      "value": 10
    },
    {
      "factor": "hypodensity",
      "points": 0,
      "present": false,
      "value": "none"
    }
  ],
  "diabetes": false,
  "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.",
  "formula": "hat",
  "formula_expression": "HAT = (diabetes OR baseline glucose >200 mg/dL) 1 (not additive) + NIHSS (<15 0, 15-20 1, >20 2) + hypodensity (none 0, <1/3 MCA 1, >1/3 MCA 2); Lou 2008; max 5; collective sICH 2/5/10/15/44% for scores 0/1/2/3/>3",
  "glucose_mg_dl": 108,
  "hypodensity": "none",
  "max_score": 5,
  "nihss": 10,
  "score": 0,
  "sich_percent": 2
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.005.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://api.magentlab.com/api/calc/hat?diabetes=false&glucose_mg_dl=108&glucose_mmol_l=6&hypodensity=none&nihss=10'

# 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://api.magentlab.com/api/calc/hat?diabetes=false&glucose_mg_dl=108&glucose_mmol_l=6&hypodensity=none&nihss=10' \
  | 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 $0.005 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.005" });
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 $0.005 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fapi.magentlab.com%2Fapi%2Fcalc%2Fhat
const res = await pay("https://api.magentlab.com/api/calc/hat?diabetes=false&glucose_mg_dl=108&glucose_mmol_l=6&hypodensity=none&nihss=10");
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 $0.005 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.005"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.get("https://api.magentlab.com/api/calc/hat?diabetes=false&glucose_mg_dl=108&glucose_mmol_l=6&hypodensity=none&nihss=10")
    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
6 h agoPassed402136 ms$0.005
16 h agoPassed402245 ms$0.005
27 h agoPassed402344 ms$0.005
36 h agoPassed402278 ms$0.005
47 h agoPassed402350 ms$0.005
Show 6 older checks
2 days agoPassed402152 ms$0.005
3 days agoPassed402225 ms$0.005
3 days agoPassed402257 ms$0.005
4 days agoPassed402189 ms$0.005
4 days agoPassed402143 ms$0.005
4 days agoPassed402140 ms$0.005