GDELT News Monitor — Global News Mentions to JSON

Search global news (GDELT, 100+ languages) by keyword and get article title, source, domain, country and date as JSON — $0.002 per article.

GDELT monitors the world’s news media in real time across 100+ languages. This actor turns a keyword into the matching global news coverage, so brand-monitoring, PR, and market-intelligence agents can track what the world is publishing about any topic as structured data.

What this actor does

• Search worldwide online news by keyword, brand, person, or event (100+ languages)
• Each result: article title, publisher domain, source country, language, publication date, URL
• Sorted newest-first; filter by postedAfter for an incremental mention feed
• Batch many terms per run; cap spend with maxResults
• Agent-ready: flat JSON with the article URL + scrapedAt for citation

You only pay for successful results — failed or empty lookups cost nothing.

Why pick this Actor

• Global news coverage across 100+ languages with domain, language, and source-country on every article
• Per-result pricing ($0.002/result) with a hard maxResults spend cap — empty lookups cost $0
• Flat, stable JSON schema with sourceUrl + scrapedAt on every item — citation-ready for RAG and grounding
• Batch many queries in one run; overlapping results are deduplicated and charged once
• MCP server, OpenAPI schema, and LangChain/CrewAI tool support out of the box — no glue code

Sample output

Each dataset item is flat, typed JSON with a sourceUrl and scrapedAt for citation/grounding:

{
  "query": "anthropic",
  "source": "gdelt",
  "title": "Anthropic launches new model",
  "domain": "techcrunch.com",
  "sourceCountry": "US",
  "postedAt": "2026-06-11T14:30:00.000Z",
  "url": "https://techcrunch.com/...",
  "sourceUrl": "https://api.gdeltproject.org/api/v2/doc/doc?query=anthropic",
  "scrapedAt": "2026-06-11T15:00:00.000Z"
}

Input

{"queries":["anthropic"]}

Field	Type	Description
queries / query	array / string	Keyword, brand, or topic. One or many.
maxResults	integer	Hard spend cap (billed per result).
keywords / postedAfter	filters	Narrow results; enable delta/scheduled runs.

How much does it cost

Pay-per-result: $0.002 per successful result. No subscription, no compute-unit guesswork, no charge for empty results. An orchestrator can cap spend with maxResults.

How to use it with AI agents (MCP), Claude, and the API

Claude Desktop / Claude Code via Apify MCP

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--actors", "oblanceolate_mandola/gdelt-news-monitor"],
      "env": { "APIFY_TOKEN": "<YOUR_APIFY_TOKEN>" }
    }
  }
}

Python (Apify API)

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("oblanceolate_mandola/gdelt-news-monitor").call(run_input={"queries":["anthropic"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

TypeScript (Apify API)

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('oblanceolate_mandola/gdelt-news-monitor').call({"queries":["anthropic"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

LangChain / CrewAI tool

from langchain_apify import ApifyActorsTool
tool = ApifyActorsTool("oblanceolate_mandola/gdelt-news-monitor")  # agent calls it autonomously

OpenAPI schema for self-integrating GPT agents is auto-exposed at the Actor's API tab.

Data & compliance

Reads only publicly accessible endpoints. No login, no credential harvesting, no CAPTCHA bypass. Every result carries its sourceUrl so downstream agents can cite and re-verify.

FAQ

How current is the news?

GDELT updates continuously; results are sorted newest-first so you see the latest coverage.

Does it cover non-English news?

Yes — GDELT monitors news in 100+ languages worldwide, with the source country on each result.

Can I monitor a brand over time?

Yes — search the term and use postedAfter on a schedule to catch only new coverage.

Can AI agents call this Actor directly?

Yes — via the Apify MCP server (snippet above), the OpenAPI schema on the Actor's API tab, or the LangChain/CrewAI tool wrapper. Results are flat JSON with sourceUrl and scrapedAt on every item, so downstream agents can cite and re-verify.

What happens when there are no results?

You pay nothing. Billing is per dataset item delivered, so an empty lookup costs $0, and the run log states why (no match, source rate limit) instead of failing silently.

Changelog

• 1.0 — Initial release: gdelt.