Content Moderate

Last 30 days

Uptime

100%

Response time

183 ms typical, 183 ms slowest 5%

Last check

3 h ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://netintel.dev/content-moderate" \
  -H "content-type: application/json" \
  -d '{"text":"I will find where you live and make you regret ever posting that."}'

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 $0.03:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fnetintel.dev%2Fcontent-moderate
const res = await pay("https://netintel.dev/content-moderate", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"text":"I will find where you live and make you regret ever posting that."}),
});
console.log(await res.json());

Example input

{
  "text": "I will find where you live and make you regret ever posting that."
}

Example output

{
  "categories": {
    "harassment": {
      "flagged": true,
      "severity": "high"
    },
    "hate": {
      "flagged": false,
      "severity": "none"
    },
    "self_harm": {
      "flagged": false,
      "severity": "none"
    },
    "sexual": {
      "flagged": false,
      "severity": "none"
    },
    "spam": {
      "flagged": false,
      "severity": "none"
    },
    "violence": {
      "flagged": true,
      "severity": "medium"
    }
  },
  "findings": [
    {
      "category": "harassment",
      "severity": "high"
    },
    {
      "category": "violence",
      "severity": "medium"
    }
  ],
  "flagged_categories": [
    "harassment",
    "violence"
  ],
  "grade": "F",
  "overall": "block",
  "reasoning": "Contains a direct threat of physical harm targeting the recipient.",
  "score": 20
}

Security scan

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

Recent checks