News Mention Alerts: New Articles from Bing News and GDELT

Give it a brand, a product, a company name or a domain and get one row for every news article that mentions it: headline, article URL, publisher, publish time and snippet, read from Bing News and, if you want worldwide coverage, from GDELT as well. An article both indexes list comes back once. Run it on a schedule and it returns only the articles it has not given you before, so a new mention reaches you the day it is published. No API key, no account, no proxy.

Who it's for

• PR and communications teams who want every new article about their brand or a product launch in a sheet or a Slack channel, without a media-monitoring subscription.
• Founders and marketers watching their own name and two or three competitors.
• Agencies who keep one watchlist per client and send a weekly coverage report.
• Sales and research teams who use a news mention of an account as a reason to reach out.
• Developers and AI agents who need fresh, de-duplicated news rows for a keyword as plain JSON.

What you get

One flat row per article:

What	Columns
The article	title, url, publisher, domain, publishedAt, snippet, imageUrl
From GDELT	seenAt, language, sourceCountry
The alert	isNew, firstSeenAt
Provenance	query, foundIn, sourceUrl, scrapedAt

Two example rows, shortened. They are real mentions of tesla, read on 2026-10-11:

query	title	publisher	domain	publishedAt	foundIn
tesla	Tesla has lined up about 90% of the power from a 450 MW solar farm rising in Arizona	Morning Overview on MSN	msn.com	2026-10-11T10:45:00.000Z	bing
tesla	Tesla renames Full Self-Driving in Europe: Assisted Driving appears on EU sites	Softonic	en.softonic.com	2026-10-11T07:28:00.000Z	bing

Rows come newest first. url is the article's own address at the publisher, with the news index's click-through redirect removed.

The two news indexes

	Bing News	GDELT
Speed	about a second per query	one request every 6 seconds, and it can refuse a run
Coverage	the articles Bing News ranks for the query, roughly 10 to 25	outlets worldwide in 65 languages
Columns it fills	publisher, publishedAt, snippet, imageUrl	seenAt, language, sourceCountry, imageUrl
Default	on	off

A value an index does not carry is empty on that row, never a guess.

How the alerts work

• A plain run (the default) returns every article found. Nothing is remembered.
• Turn on "Only return mentions that are new" and the run remembers what it returned. The first run returns the articles already out there, so you start with the current picture. From then on a run returns only articles it has not returned before. A run with nothing new returns nothing and charges nothing beyond the start fee.
• Give the watchlist a name to keep two watches apart, or to track while still getting every article back on every run, with isNew and firstSeenAt filled.

Three rules keep the alerts honest:

1. Filters come before the memory. An article left out by "Published in the last N days", by "Only rows containing" or by "Skip rows containing" is not remembered.
2. Only what you received is remembered. A row cut by "Mentions per query", by the result limit or by your spending limit is returned on the next run.
3. A failed read changes nothing. If an index could not be read, the memory is left as it was and the next run compares against the same baseline.

How to use News Mention Alerts

1. In the Apify Console. Open the actor page and click Start — the queries field is already pre-filled with a working example. Results land in the run's dataset as soon as each item is found.
2. Via the API. Call it directly with a POST request — no Console needed once you have an API token:

   curl "https://api.apify.com/v2/acts/accountable_eel~news-mention-alert-composite/run-sync-get-dataset-items?token=<YOUR_TOKEN>" \
     -X POST \
     -H "Content-Type: application/json" \
     -d '{"queries":["tesla"]}'
   

3. On a schedule. Save this actor as an Apify Task with the input you want, then add a Schedule (hourly, daily, weekly) so it runs on its own — no server of your own required.

Input

{
  "queries": [
    "tesla"
  ]
}

One per line. Each line is searched as typed in the news indexes you select, and every article that mentions it comes back as one row. Put a name of several words in double quotes to match it as an exact phrase. Meant for brands, products, organisations and domains, not for private individuals. Accepted formats: tesla, "Novo Nordisk", apify.com.

Output

One row per article, for example:

query	found	status	title	url	sourceUrl	publisher	domain	publishedAt	seenAt	snippet	imageUrl	language	sourceCountry	foundIn	isNew	firstSeenAt	scrapedAt
tesla	true	OK															1970-01-01T00:00:00.000Z

A query with no article, and a query whose news index could not be read, come back as one row with "found": false and a message that says which. It is never charged.

Example runs

Three inputs that need no credentials of any kind and return rows as they stand. Paste one into the Input tab and press Start.

1. What is the news saying about this brand right now?

{
  "queries": ["tesla"],
  "sources": "bing",
  "maxItems": 20
}

2. A daily alert that only returns articles you have not seen

Save this as a task and put it on a daily schedule. The first run returns the current articles; later runs return an article only the first time it is seen.

{
  "queries": ["\"Novo Nordisk\"", "wegovy"],
  "sources": "bing",
  "onlyNewSinceLastRun": true,
  "deltaName": "brand-press"
}

3. Worldwide coverage of a product in the last three days, both indexes

{
  "queries": ["iphone"],
  "sources": "both",
  "sinceDays": 3,
  "maxItems": 50
}

Pricing

Pay-per-event. A flat per-run fee covers session/proxy warmup; each independent source is billed under its own event, only when that source actually returns data — see .actor/pay_per_event.json for exact prices. A miss is never charged.

You pay once per article returned, and nothing else:

• A query with no article is free.
• A query whose news index could not be read is free.
• An article listed by both indexes is one row and one charge.
• With "Only return mentions that are new" on, an article you were already given is not returned and is free. A quiet day costs the start fee and nothing more.
• Use "Mentions per query" and "Stop after this many results" to put a ceiling on a run.

Use it from Clay, n8n, Make, or an AI agent

This actor runs synchronously over plain HTTP — call it directly from a script, a workflow tool, or an AI agent, no Apify Console needed once you have an API token.

curl "https://api.apify.com/v2/acts/accountable_eel~news-mention-alert-composite/run-sync-get-dataset-items?token=<YOUR_TOKEN>" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{"queries":["tesla"]}'

n8n. Add an HTTP Request node: Method POST, URL https://api.apify.com/v2/acts/accountable_eel~news-mention-alert-composite/run-sync-get-dataset-items?token=<YOUR_TOKEN>, Body Content Type JSON, JSON Body {"queries":["tesla"]} (swap in an expression from an earlier node for a real value).

Clay. Add an "HTTP API" column: Method POST, URL https://api.apify.com/v2/acts/accountable_eel~news-mention-alert-composite/run-sync-get-dataset-items?token=<YOUR_TOKEN>, Body {"queries":["{{news mention}}"]}, mapping the row's news mention into the queries array.

MCP. In Claude, Cursor, or any MCP client with the Apify MCP server, ask for "news mention alerts" — the agent will find and run this actor.

Where the data comes from

• Bing News publishes its search results as an RSS feed. The actor reads that feed, newest first, and tops the list up from Bing's default ranking when the newest-first pages run short.
• GDELT is an open index of world news. The actor reads its article list for your query, newest first, limited to the days you asked for.

Google News is not read.

Limits, stated plainly

• This is a sample of the news, not all of it. Bing News lists the articles it ranks for a query, roughly 10 to 25 at a time. Run it daily and the watch accumulates; a single run is not an archive search.
• GDELT is slow and sometimes closed. It allows one request every few seconds for everyone on the same address. When it refuses, the run says so in the log, returns the Bing News rows and tries GDELT again on the next run. With GDELT as the only index, a refused query is a free found: false row.
• GDELT rows have no publisher name, publish time or snippet. They carry the time GDELT first saw the article, its language and the outlet's country.
• GDELT headlines are machine-normalised, with spaces around punctuation.
• De-duplication is by article address. The same wire story republished by two outlets is two rows, because it is two articles. A mobile or AMP address of the same article can also come back as a second row.
• A domain is searched as a word. apify.com finds articles in which that text appears.
• Results are in the language and market the index picks for the query. There is no country or language setting in this version.
• No article body. The row carries headline and snippet, not the full text.
• Not for watching private individuals. It is built for brands, products, organisations and domains, and returns no author or contact details.

Data & privacy

Everything returned is what two public news indexes list about published articles: headline, address, outlet, time. No author, reader or contact data is read. The memory the actor keeps between runs is a list of article addresses per query, stored in a key-value store in your own Apify account under the watchlist name you chose.

FAQ

Why did a run return fewer rows than "Mentions per query"? That number is a ceiling. Bing News lists a limited set of recent articles per query; turn GDELT on for more, or widen "Published in the last N days".

Why did my scheduled run return nothing? Nothing new was published since the last run, so nothing was returned or charged.

Why is publisher empty on some rows? The article was found in GDELT only, and GDELT lists the outlet's domain and country, not its name. domain is always filled.

Can I watch several brands in one run? Yes, one per line. Each query keeps its own memory, so adding one later does not reset the others.

How often should I run it? Daily suits most brands. Hourly makes sense during a launch or a crisis.

Do I need a proxy or an API key? No.

Related actors

• Google News Lookup for a one-off Google News search.
• Hacker News Mentions Monitor for mentions in stories and comments on Hacker News.
• Bluesky Mentions Monitor for mentions in Bluesky posts.