News Monitor: Keyword News Alerts + RSS/Atom Feeds, Deduplicated, with Company Tags

Track the news for any keyword, company or topic, plus your own publisher RSS/Atom feeds, and get only the new articles since your last run. The same story syndicated across many sites is collapsed into one item (canonical URL plus title-similarity matching), with the other outlets listed under alsoReportedBy. Add a watchlist (company names, tickers, aliases) and each article is tagged with the companies and tickers it mentions. Schedule it every hour for a clean news feed in Slack, email, Sheets or your app.

Where the news comes from

• Keyword search: the GDELT Project DOC 2.0 API, an open, free index of world news in 100+ languages, updated every 15 minutes. GDELT rate-limits busy cloud IP ranges, so on some runs it refuses requests; the run then continues with your feeds and notes it in RUN_SUMMARY.errors. For dependable coverage, add the publisher feeds you care about.
• Keywords also filter your feeds: when you give both, feed items must mention one of your keywords (whole-word match).
• Your feeds: any RSS 2.0 or Atom feed you add. The Actor checks each site's robots.txt first and skips disallowed feeds. You are responsible for using feeds within their publishers' terms.
• Google News RSS is not used. Its feed terms allow only personal, non-commercial feed readers, which rules out a paid tool.

For AI agents (MCP / API) quick reference

• Use when: you need recent news articles for keywords or companies, deduplicated, with only new items since the last check, or company/ticker tags for a watchlist.
• Don't use for: full article text (only title, link, date, source and the feed summary are returned), paywalled content, or social media.
• Minimal input: {"searchQueries": ["Nvidia"], "maxItems": 20}.
• Output: one dataset item per new article: title, url, canonicalUrl, source, publishedAt, summary, language, sourceCountry, imageUrl, companies, tickers, matchedQuery, foundVia (gdelt or feed), alsoReportedBy.
• Price: $0.001 per new article, no start fee. Duplicates and already-seen articles are free. Pay per event only, limited permissions, so agentic payments (x402, Skyfire, Apify AGI token) work.
• MCP: add https://mcp.apify.com?tools=kempt_horizon_yzk/news-monitor to your MCP client.

What can it do?

• ✅ Keyword news search across global news via GDELT, with quotes, OR and minus
• ✅ Your RSS/Atom feeds in the same output, with robots.txt checked first
• ✅ Cross-source deduplication by canonical URL (tracking parameters, AMP and www removed) and title similarity
• ✅ Watchlist tagging for companies, tickers and aliases, with an option to keep only matching articles
• ✅ Monitor mode on by default: remembers 30 days of URLs and titles in a key-value store and returns only new stories

Who uses it?

PR and comms teams, investor relations, traders and analysts following tickers, competitive intelligence, newsletter editors, and AI agents that need fresh news.

How much does it cost?

Event	Price
New article	$0.001

Hourly monitoring of 10 keywords that finds 300 new articles a day costs about $0.30 a day.

Input example

{
  "searchQueries": ["Nvidia", "\"data center\" AND power"],
  "feeds": ["https://techcrunch.com/feed/", "https://feeds.bbci.co.uk/news/business/rss.xml"],
  "watchlist": ["Nvidia|NVDA|GeForce", "Alphabet|GOOGL|Google", "Microsoft|MSFT|Azure"],
  "lookbackHours": 24,
  "maxItems": 200,
  "onlyNew": true,
  "stateKey": "ai-chips-news"
}

Output example

{
  "title": "Adobe Rebuilt Photoshop And Premiere For NVIDIA RTX Spark Platform",
  "url": "https://www.engadget.com/2287388/adobe-rebuilt-photoshop-and-premiere-for-nvidia-rtx-spark/",
  "canonicalUrl": "engadget.com/2287388/adobe-rebuilt-photoshop-and-premiere-for-nvidia-rtx-spark",
  "source": "engadget.com",
  "publishedAt": "2026-10-15T13:30:00Z",
  "summary": null,
  "language": "English",
  "sourceCountry": "Japan",
  "imageUrl": "https://www.engadget.com/img/gallery/adobe-rebuilt-photoshop-and-premiere-for-nvidias-rtx-spark-platform/l-intro-1792065422.jpg",
  "companies": [
    "Nvidia"
  ],
  "tickers": [
    "NVDA"
  ],
  "matchedQuery": "Nvidia",
  "foundVia": "gdelt",
  "feedUrl": null,
  "alsoReportedBy": [],
  "scrapedAt": "2026-10-15T14:09:14.740Z"
}

FAQ

Why is a keyword article's title missing my keyword? GDELT matches the full article text, not just the title.

Does it return full article text? No. Use the URL to read the article on the publisher's site.

Built and maintained by Kempt Horizon Data. Found a bug or need a field? Open an issue on the Actor's Issues tab and we usually reply within a day. Not affiliated with GDELT, Google or any publisher.