Global news intelligence, as an API

265sources

14,725articles

331live events

43,798entities

35languages

Live

Query the real API.

Not a mock. This runs against the production engine, server-side, and returns the same JSON a client gets.

kontext-api live

GET /v1/search?q=Nvidia&limit=4

{
    "query": "Nvidia",
    "results": [
        {
            "title": "SpaceX: SpaceX kauft laut Bericht KI-Chips für 40 Milliarden Dollar bei Nvidia",
            "source": "www.zeit.de",
            "category": "business",
            "region": "europe",
            "published_at": "2026-10-07T05:33:12+00:00"
        },
        {
            "title": "Sources: Nico Caprez, son-in-law to Jensen Huang, rapidly ascended to become an Nvidia VP, serv...",
            "source": "www.techmeme.com",
            "category": "tech",
            "region": "global",
            "published_at": "2026-10-05T13:55:03+00:00"
        },
        {
            "title": "Elon Musk will KI-Chips von Nvidia für 40 Milliarden Dollar kaufen",
            "source": "www.welt.de",
            "category": "business",
            "region": "europe",
            "published_at": "2026-10-07T02:43:38+00:00"
        },
        {
            "title": "SpaceX seeks $40 billion financing led by Apollo to buy Nvidia chips, FT reports - Reuters",
            "source": "news.google.com",
            "category": "general",
            "region": "global",
            "published_at": "2026-10-06T23:19:20+00:00"
        }
    ]
}

try

Pipeline

From raw feeds to structured events.

Deterministic stages, no hallucination. Every article is normalized, de-duplicated, enriched and clustered into events.

01IngestRSS / API / sitemap

02Normalizetext, lang, url

03Dedupexact + simhash

04EnrichNER, category, geo

05Clusterarticles to events

06Claimsv2

07IndexFTS + trigram

08ServeREST + MCP

Capabilities

What you get back.

01

Structured, not raw

Every story tagged by region, category and domain, with the people and companies it mentions.

02

Events, not duplicates

The same story from many outlets becomes one event, with every source attached.

03

Entities and relations

A knowledge graph of people, organisations and places, with stable identifiers.

04

Full-text and fuzzy search

Query by keyword, filter by region, category, domain, language or date.

05

Scored and de-duplicated

Authority, freshness and cross-source confirmation produce one relevance score.

06

Agent-ready

A REST API and an MCP server, so developers and AI agents can query the world in one call.

API

Seven endpoints. One call.

GET	`/v1/stats` corpus totals and coverage
GET	`/v1/articles` filter by category, domain, region, lang, since
GET	`/v1/articles/{id}` article + sources + entities + events
GET	`/v1/events` cross-source events
GET	`/v1/events/{id}` event + its articles
GET	`/v1/sources` the source registry
GET	`/v1/search` full-text + fuzzy search

curl "https://api.kontextnews.online/v1/search?q=Nvidia&limit=5" \
  -H "X-API-Key: kn_live_..."

Per-key rate limits. JSON responses. Keys shown once, stored hashed.

Coverage

Every continent, one schema.

Top outlets and wires from around the world, normalized into a single structure and updated continuously.

Europe 49 · North America 31 · Latin America 37
Asia 35 · Africa 35 · Middle East 19
Oceania 19 · Global wires / AI / dev 40

Who it is for

Built for people who work with news.

Developers

Ship on structured news

One REST API and MCP server instead of scraping dozens of feeds.

Journalists

Monitor the world

Saved queries, events and timelines, delivered where you work.

Publications

One source, many outlets

Our publications consume the same engine through an API key.

AI agents

Query the world

An agent-native surface: search news, events, entities and timelines.

Pricing

Plans

Monthly subscriptions in EUR, cancel anytime. Full details on the pricing page.

Free

€0/mo

1,000 requests / month
10 requests / minute
1 API key

Start free

Pro

€29/mo

100,000 requests / month
Monitors and reports
Email delivery

Business

€99/mo

500,000 requests / month
Priority routing
Webhooks

Enterprise

€299/mo

2,000,000+ requests / month
Custom sources
SLA and redistribution

FAQ

Questions, answered.

What is KontextNews?

An API that turns the world's news into structured, queryable data: articles, cross-source events, entities and relations, from top outlets on every continent.

Where do the sources come from?

265 validated feeds and wires across Europe, North America, Latin America, Africa, Asia, the Middle East and Oceania, each scored for authority. Dead and empty feeds are removed automatically.

How fresh is the data?

Feeds are polled continuously. Search is ranked with a 30-day recency half-life, so fresh reporting outranks older archive that merely matches the query.

Is this original reporting or aggregation?

Aggregation. Every item links back to its source. We add the structure on top: classification, de-duplication, events and entities.

How does search work?

Hybrid search: PostgreSQL full-text plus trigram similarity, blended with a freshness weight. Filter by category, domain, region, language and date. See Search & ranking.

Is there an MCP server for AI agents?

Yes. The same engine is exposed as a REST API and an MCP server, so agents can query news, events and entities in one call.

What are the rate limits?

Per key and per plan, from 10 requests per minute on Free up to a custom limit on Enterprise. Exceeding it returns 429 with a Retry-After header. See Rate limits.

Can I redistribute the data?

Redistribution is covered by the Enterprise plan. Lower tiers are for internal use and products that link back to the source.

Global news intelligence, as an API.