Tools / Google Maps / Scraper
Tell your agent the kind of business and the city. RouterGrowth returns what Google Maps lists for that search as rows: name, category, address, phone, website, rating, review count and whether the owner claimed the listing, ready to filter, enrich or export.
Ask your agent
List 100 dental clinics in Phoenix with their website, phone and rating, and flag the ones under 4 stars.
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 local.places (google maps places), run through RouterGrowth on October 17, 2026. These are the first rows it returned; fields that name a person are masked.
| name | category | rating | reviews_count | domain |
|---|---|---|---|---|
| Cenizo - Downtown | Coffee shop | 5 | 17 | cenizoatx.com |
| Caroline | Coffee shop | 4.8 | 15693 | www.carolinerestaurant.com |
| Halcyon | Coffee shop | 4.3 | 2073 | www.halcyoncoffeebar.com |
Coffee shops in Austin, Texas: the first 20 places Google Maps listed for the search, each with its phone, address and coordinates as well.
Step by step
Add the MCP server to Claude, ChatGPT, Claude Code, Codex or Cursor. A new workspace starts with $1 of credit, enough to run this example many times.
Give a category and a location written as city, state and country. local.places returns the listings Google Maps shows for that search.
Ask for the places under four stars, the ones without a website, or the ones whose owner never claimed the listing. The agent filters what it already has.
Read the recent reviews of the places you keep with reviews.search, or find a work email from the website's domain with contact.find.
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.
List 100 dental clinics in Phoenix with their website, phone and rating, and flag the ones under 4 stars.
Find the coffee shops in Austin that have no website and give me their phone numbers.
For each restaurant on this list, read the last 20 reviews and tell me the complaint that repeats.
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 local.places -i '{"query": "coffee shop", "location": "Austin,Texas,United States", "limit": 20}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "local.places", "input": {"query": "coffee shop", "location": "Austin,Texas,United States", "limit": 20}}'Worth knowing
A call returns one page of listings for the query and the location. To cover a whole city, the agent runs the category across neighbourhoods and removes duplicates.
local.places is charged per search, not per seat or per month, and the quote is shown before the call.
The domain on each listing is what the next step needs: reviews, the owner's name or a work email, on the same key.
FAQ
No. The call runs on RouterGrowth's providers with your RouterGrowth key: no Google Cloud project and no Places API billing of your own.
Name, category, address, phone, website and domain, rating, review count, coordinates, the place ID and whether the owner claimed the listing.
Yes. reviews.search returns recent reviews for a place with rating, text, date and the owner's reply when there is one.
One page of results for the query and the location, 20 by default. For a whole city the agent runs several searches and merges them.
Ask the agent for a CSV or a table. The rows come back as structured data, so the export is one instruction.
More on Google Maps
Reading this as an agent? This page as markdown: /tools/google-maps/scraper.md
Connect your agent once. The first calls run on the $1 that comes with signup.