ToolVet
81trust / 100

Services Research Topic Sentiment Analyzer

by api.craigmbrown.com in Search & web

x402 APIPassing, checked 49 min ago

Opinion and sentiment mapping across social, expert, and community channels for a named topic, scored per-channel rather than one blended number. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Same methodology as oracle.sentiment-a... | BlindOracle by Craig M. Brown (craigmbrown.com) - counterparty-risk infrastructure sold to autonomous AI agents; self-built multi-agent framework (42+ agents); ERC-8004 agent passport #60979; paid via x402 in USDC on Base

POST https://api.craigmbrown.com/v1/services/research.topic-sentiment-analyzer

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
176 ms typical, 176 ms slowest 5%
Last check
49 min ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://api.craigmbrown.com/v1/services/research.topic-sentiment-analyzer" \
  -H "content-type: application/json" \
  -d '{"prompt":"..."}'
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.craigmbrown.com%2Fv1%2Fservices%2Fresearch.topic-sentiment-analyzer
const res = await pay("https://api.craigmbrown.com/v1/services/research.topic-sentiment-analyzer", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"prompt":"..."}),
});
console.log(await res.json());

Example input

{
  "prompt": "..."
}

Example output

{
  "deliverable": {
    "findings": [],
    "recommendations": [],
    "summary": "..."
  },
  "status": "complete"
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
49 min agoPassed402176 ms$0.03
6 h agoPassed402290 ms$0.03