Tools / Web search and scraping / API
Put a listed company's name and ticker in the query and news.search returns recent articles on it: headline, source, snippet, URL and publication time, from financial press and tech sites. It is news, not market data: no quotes, prices, filings or sentiment scores come back, so pair it with your own price feed.
Ask your agent
Get today's news on NVDA, AMD and AVGO and list each headline with its source and time.
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 |
|---|---|---|
| 2026-10-26 | www.wsj.com | Two AI Chipmakers Make Up 34% of America’s Earnings Boom |
| 2026-10-25 | www.cnbc.com | Nvidia's role as AI financier faces first big test as neoclouds take market hit |
| 2026-10-25 | www.barchart.com | Nvidia vs. Broadcom: One Grew AI Revenue 221% Last Quarter. The Other Grew 117%. |
Ten articles for NVIDIA stock NVDA from the WSJ, CNBC, Barchart, Yahoo Finance, Seeking Alpha and others, all dated within the last four days.
Step by step
Use both, such as NVIDIA stock NVDA, to keep results on the company.
Send the query and a limit. The articles are in result.articles.
Drop URLs you already stored, so each refresh shows only fresh headlines.
Match articles to your own price data by date when you look at moves.
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 today's news on NVDA, AMD and AVGO and list each headline with its source and time.
Pull news on the five listed competitors in our space and scrape the two newest 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": "NVIDIA stock NVDA", "limit": 8}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "news.search", "input": {"query": "NVIDIA stock NVDA", "limit": 8}}'Worth knowing
No share prices, volumes, filings or analyst ratings come back. The call returns articles.
A ticker alone can match unrelated words. The company name with it keeps the list on topic.
Publication times come from labels such as 5 hours ago, so treat them as the day of the article.
FAQ
No. It returns news articles about the company, not market data.
One query per call. Run one per company, in parallel if you like.
No. Read the snippets, or pass them to a model to score.
Set location to a country to search that market's news, such as Germany or Japan.
More on Web search and scraping
Reading this as an agent? This page as markdown: /tools/web-scraping/stock-news-api.md
Connect your agent once. The first calls run on the $1 that comes with signup.