Tools / Web search and scraping / API
Send a topic to news.search, with a location and language when you need them, and get recent articles as JSON: title, source domain, snippet, URL, publication time and an image link. Results default to the United States. Use it to follow a market, a competitor or a category without reading news sites one by one.
Ask your agent
Get this week's news on battery recycling and group the articles into funding, partnerships and regulation.
Connect RouterGrowth once, then ask in plain words. New workspaces start with $1 of credit. Get a key or read the setup guide.
A real run
One call to news.search (news search), run through RouterGrowth on October 26, 2026. These are the first rows it returned; fields that name a person are masked.
| published | source | title |
|---|---|---|
| 2026-10-23 | electrek.co | Redwood and Rivian set to expand their EV battery recycling partnership |
| 2026-10-23 | www.recyclingtoday.com | NEU Battery Materials closes $7.6M funding round |
| 2026-10-26 | www.greensboro-nc.gov | Skip the Bin. Turn Your Batteries In. |
Ten articles for battery recycling from the last week: an EV recycling partnership, a funding round, city disposal rules and new recycling labs, from trade press and local sites.
Step by step
A few words work best: a category, a company or an event.
Send query, and location or language if the market is not the United States.
Order the articles by time and drop the URLs you already have.
Run web.scrape on an article URL for the full text.
Price
List prices on this call, read from the catalog when this page was built. The exact figure is quoted before every run, and a monthly plan lowers it.
In practice
You describe the job; the agent picks the calls, shows the price and runs them.
Get this week's news on battery recycling and group the articles into funding, partnerships and regulation.
Find news on our three biggest competitors and scrape the two most recent articles about each.
Connect
One MCP server for Claude, ChatGPT, Claude Code, Codex and Cursor, or the same call over the CLI and REST with the input above.
claude mcp add --transport http routergrowth https://api.routergrowth.com/mcp
npm install -g routergrowth && routergrowth setup
routergrowth run -c news.search -i '{"query": "battery recycling", "limit": 8}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "news.search", "input": {"query": "battery recycling", "limit": 8}}'Worth knowing
Publication times come from labels such as 3 hours ago, so trust the day more than the minute. Some articles have no time.
Articles are fetched ten at a time, so a limit under ten can still return ten.
Each article carries a short snippet. Scrape the URL when you need the story itself.
FAQ
Pass a country, or a city and country, in location. The default is the United States.
No. It returns title, source, snippet, URL and time. Use web.scrape for the text.
Yes. Set language along with the location.
Results lean recent but follow relevance, so older articles can appear. Check published_at.
More on Web search and scraping
Reading this as an agent? This page as markdown: /tools/web-scraping/news-api.md
Connect your agent once. The first calls run on the $1 that comes with signup.