Built for context windows, not front pages.
Live news, deduplicated into events — no key required.
01 — Try it
Pick a use case — see the call and the event it returns.
02 — The tools
Three free, two on Enterprise.
Keyword, language, source, country — ranked and clustered.
Any company, deduplicated into events.
What's developing now, ranked by momentum.
The same, scoped to local and regional outlets.
Standing queries push new events to your endpoint.
03 — License and limits
Ship what you build on it — in production. Pay only when you need more calls.
04 — NewsMCP or NewsCatcher
NewsMCP is for agent runs. NewsCatcher is for systems that depend on news.
Keyless, clustered events, token-lean. Reach for it over MCP or its API inside Claude, Cursor, or an agent loop. The go-to for exploration and one-off runs.
When a business process runs on news: 2.5B+ articles indexed across 7+ years, 40+ filters, 30+ data fields, SLAs, and SOC 2 Type II.
05 — FAQ
No key to start — keyless runs at 20 calls an hour, looks back about 24 hours, and returns up to 8 events per call. Add a free account and API key for 100 calls an hour, a ~30-day window, and up to 100 events.
Yes. Every plan includes a full commercial license, keyless included — ship what you build from day one.
Either. The same tools return the same event objects over MCP and a plain REST API. Use whatever your stack prefers.
Copy the setup snippet from "Setup for agents" into your client config. It works anywhere MCP does — Claude, Cursor, or your own agent loop.
New stories land in the index continuously and are searchable within minutes of publication.
One real-time news index, built and run entirely in house by NewsCatcher — no third-party search API sitting in the loop.
Worldwide sources across dozens of languages. Scope any query by language, country, or source.
Automatically. The same story from many outlets is clustered into one event, so your agent reads a single result instead of thirty near-identical articles.
Story events, not a flat article list. Each event carries an event_id, an article_count, an event_score, and its articles — each with title, summary, link, published date, theme, and sentiment.