The AskNews platform Live News Search
Give your AI the latest news context
Bring current reporting, including licensed news sources, into your AI application. Retrieve prompt-ready text or structured article records with source links and publication dates, without building a news ingestion pipeline.
For news-aware agents, research tools and time-sensitive answers.
$ asknews research "Investigate the effect of Fed rate policy on Nvidia and AMD"
AI companies raise token prices to cover development costs
Fed signals rate pause, tech stock lead the rally
Chipmakers rethink capex as borrowing costs shift
Startups see cheaper credit as financing costs cool
Rare earth elements carry the AI boom—but at what cost?
From breaking news to AI-ready context
When a question depends on what is happening now, your application needs reporting it can retrieve and inspect. AskNews News Search finds relevant articles and returns enriched context for your model or data workflow.
Licensed sources you cannot scrape
AskNews holds formal licensing agreements with AP, AFP, Newstex and over a thousand publishers worldwide. Roughly half of all news sits behind a hard or soft paywall, and that share is growing — this is the reporting generic web search structurally cannot reach. With AskNews, your application gets it legally, with publishers compensated through a 50/50 revenue share.
Every claim traces back to its source
Each article carries its URL, publication date and publisher. When a model asserts something, you can follow it to the reporting it came from — the difference between an answer you can audit and one you have to trust. That trail is what makes AskNews usable in forecasting, risk and intelligence work where a conclusion has to be defensible.
Why teams choose AskNews for news context
- Scraping is brittle and legally exposed; AskNews is licensed, publisher-aligned and does not break when a site adds Cloudflare.
- General web search returns noisy, unlicensed HTML. AskNews returns cleaned, enriched, prompt-ready context, so downstream token costs fall rather than rise.
- Source links and publication dates travel with every article, so analysts and auditors can trace any claim back to the reporting behind it.
What comes back
- Prompt-ready news text, structured article records, or both, according to your requested return type.
- Article URLs and publication dates to inspect and cite in your workflow.
- Available enrichments such as summaries, entities, categories and sentiment.
MCP, CLI and SDK quickstart
Give your agent licensed news context in minutes
Run a first query from your terminal, connect AskNews as an MCP tool, or call the News Search API from Python, TypeScript or PHP. No scrapers, parsers or news RAG pipeline to maintain. Use Historical News Search when you need the archive.
Build vs buy
The pipeline is never just a pipeline
Teams that build their own news ingestion budget for a crawler and a parser. What arrives is bot detection, paywalls they cannot lawfully pass, per-publisher markup that changes without notice, deduplication, language coverage, and managing an archive for low-latency retrieval. It is a product, and it competes for the engineers you hired to build your own.
Read: Why your team shouldn't build its own news ingestion pipelineBuild
- Crawler + bot detection
- Per-publisher parsers
- Dedupe + language coverage
- Archive consistency
- Ongoing maintenance
Buy
ask.news.search_news(
query="...",
return_type="string",
)Licensed sources, enriched and prompt-ready, with the links and dates already attached.
Start with a question your application needs to answer
Retrieve the reporting, inspect the sources and see how the context fits your workflow.