Agent402 / tools / search

Web search

$0.01 per call · USDC via x402 · GET /api/search

Live web search: ranked results (title, URL, snippet, age) from an independent search index as clean JSON — fresh pages your model's training cutoff has never seen. Optional freshness filter (pd/pw/pm/py = past day/week/month/year).

Input

FieldTypeDescription
q *stringSearch query (max 400 chars)
countnumberResults to return, 1-20 (default 10)
freshnessstringOptional: pd, pw, pm, or py (past day/week/month/year)

Example output

{
  "query": "x402 payment protocol adoption",
  "count": 5,
  "results": [
    {
      "title": "x402: An open standard for internet-native payments",
      "url": "https://www.x402.org/",
      "description": "HTTP 402 brought to life…",
      "age": null
    }
  ]
}

Try it — see the 402 challenge (free)

curl -i "https://agent402.tools/api/search?q=x402+payment+protocol+adoption&count=5"

The response is HTTP 402 Payment Required with exact payment requirements. Any x402 v2 client pays automatically and retries:

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/search?q=x402+payment+protocol+adoption&count=5");

Wallet-only. This tool reaches the network/browser/storage, so it is paid in USDC via x402 (no proof-of-work tier).

Related tools

Extract article

USDC $0.005 · POST /api/extract

Extract the main article content from any public URL as clean markdown. Returns title, byline, excerpt, word count, and …

Page metadata

USDC $0.002 · GET /api/meta

Fetch page metadata for a URL: title, description, OpenGraph, Twitter cards, canonical URL, favicon.

Browser render

USDC $0.02 · POST /api/render

Render a page in a real headless Chromium browser (JavaScript executed), then extract the main content as clean markdown…