Keyword extraction
POST /api/keywordsTop keywords and two-word phrases by frequency (stopwords removed). Cheap, deterministic signal for routing, tagging, and dedup.
Input
| Field | Type | Description |
|---|---|---|
text * | string | Text to analyze (max 500KB) |
limit | number | Max keywords (default 15) |
Example output
{
"keywords": [
{
"term": "payment",
"count": 9
}
],
"phrases": [
{
"term": "x402 protocol",
"count": 4
}
]
}
Try it - see the 402 challenge (free)
curl -i -X POST https://base-sentinel-production.up.railway.app/api/keywords \
-H "Content-Type: application/json" \
-d '{"text":"Long article text…","limit":10}'
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://base-sentinel-production.up.railway.app/api/keywords", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
"text": "Long article text…",
"limit": 10
}),
});
No wallet? Pay with compute
This is a pure-CPU tool, so an agent without a wallet can pay with proof-of-work instead of USDC: fetch a challenge, solve the sha256 puzzle (16 leading zero bits - a fraction of a second of CPU, no money, no AI tokens), and resend with the X-Pow-Solution header.
import { createHash } from "node:crypto";
const lz = (b) => { let t = 0; for (const x of b) { if (!x) { t += 8; continue; } t += Math.clz32(x) - 24; break; } return t; };
const c = await (await fetch("https://base-sentinel-production.up.railway.app/api/pow/challenge?slug=keywords")).json();
let n = 0;
while (lz(createHash("sha256").update(c.challenge + ":" + n).digest()) < c.difficulty) n++;
await fetch("https://base-sentinel-production.up.railway.app/api/keywords", { method: "POST", headers: { "X-Pow-Solution": c.token + ":" + n, "Content-Type": "application/json" }, body: JSON.stringify({"text":"Long article text…","limit":10}) });
Part of these workflows
This tool is one step in 2 curated multi-tool workflows - agents can fetch the whole sequence as an MCP prompt or call https://base-sentinel-production.up.railway.app/api/skill-packs/{slug}/prompt.
- Content grade - Grade a page's content quality - extract the readable content then analyze keyword density.
- Feed watch - Monitor an RSS/Atom feed in one call: parse the feed, read the top story in full, extract the keywords driving the cycle, and diff the item list against your last run to isolate what's new.
Related tools
Slugify
POST /api/slugifyTurn any text into a URL-safe slug (lowercase, hyphenated, diacritics stripped).
try in playground →Case convert
POST /api/caseConvert text between camelCase, PascalCase, snake_case, kebab-case, CONSTANT_CASE, Title Case, lower, UPPER.
try in playground →Text statistics
POST /api/text-statsCharacters, words, sentences, paragraphs, average word length, reading time, and an LLM token estimate for any text.
try in playground →