Tools / Google Search / Scraper
Scraping Google yourself means proxies, CAPTCHAs and a parser that breaks when the page changes. seo.serp does the fetch on a SERP provider and hands back the parsed page: positions, titles, URLs, snippets, the features present and the sources an AI Overview cited.
Ask your agent
Scrape Google in Boston for best running shoes and tell me which review sites the AI Overview cites.
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 seo.serp (live serp results), run through RouterGrowth on October 19, 2026. These are the first rows it returned; fields that name a person are masked.
| position | domain | title |
|---|---|---|
| 2 | www.treelinereview.com | Best Road Running Shoes for Men of 2026 |
| 3 | www.runnersworld.com | The 7 Best Running Shoes for Beginners in 2026, Tested ... |
| 5 | health.yahoo.com | Best running shoes of 2026, tested by real runners and ... |
Google in Boston for best running shoes: review sites on top, a forums block, and an AI Overview citing three sources that the response lists.
Step by step
There is no proxy, browser or CAPTCHA service to configure. The call needs only a keyword.
Use City,State,Country for city level results; the response confirms the resolved location.
Organic results come with position, title, URL, domain and snippet, plus serp_features and ai_overview_sources.
Pass the top URLs to web.scrape to read their content.
Price
List prices on Google, 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.
Scrape Google in Boston for best running shoes and tell me which review sites the AI Overview cites.
Scrape the top five results for this keyword and compare their headings with our page.
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 seo.serp -i '{"keyword": "best running shoes", "location": "Boston,Massachusetts,United States"}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "seo.serp", "input": {"keyword": "best running shoes", "location": "Boston,Massachusetts,United States"}}'Worth knowing
The fetch runs on the provider's side. A failed search moves to a fallback under your cap, or is not charged.
You get fields, not the page source. Use web.scrape when you need the HTML of a result.
When Google shows an AI Overview, the cited URLs come back in ai_overview_sources when the provider sees them.
FAQ
No. The scraping runs on the SERP provider.
No. The call returns parsed results and features.
The first page of organic results, usually eight to ten after ads and blocks are set aside.
Yes. Set engine to bing.
More on Google Search
Reading this as an agent? This page as markdown: /tools/google-search/serp-scraping-api.md
Connect your agent once. The first calls run on the $1 that comes with signup.