Start free

Platforms MCP server

MCP server · 3 tools · 4 endpoints

Google Maps MCP server

Place search, place details and photos for location research, with honest notes on the contacts path.

Get a free key Connect in a minute

100 credits on signup · No card · Sign in with OAuth or paste a key

scrapersocial-google_maps mcp.scrapersocial.com/google_mapsconnected

you

Find the 20 highest-rated <category> in <city> and list them with addresses and rating counts.

agent

calls search 2 credits / place

{ "query": "<keywords>" }

server

returns

places [{ … }] · one per place

Shape only. Keys follow the tool's summary; a real call returns the full record. 1 call · 2 credits

Connect

One URL. Your client already knows what to do with it.

The first call opens a sign-in. New accounts get 100 credits, no card. Every client below shares one account and one balance.

Get a free key

server url https://mcp.scrapersocial.com/google_maps

claude.aiOAuth

Settings → Connectors → Add custom connector, then paste the server URL.

mcp.scrapersocial.com/google_maps

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

$ claude mcp add --transport http scrapersocial-google_maps https://mcp.scrapersocial.com/google_maps

Approve the sign-in prompt on first use.

Cursorone click

Installs the server and opens the MCP panel.

Add to Cursor

or paste the JSON into .cursor/mcp.json

{
  "mcpServers": {
    "scrapersocial-google_maps": {
      "url": "https://mcp.scrapersocial.com/google_maps",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

Other clients · VS Code, Windsurf, Gemini CLI, anything that speaks MCP

VS Codeone click or JSON

Add to VS Codeor run MCP: Add Server, choose HTTP and use:

{
  "name": "scrapersocial-google_maps",
  "type": "http",
  "url": "https://mcp.scrapersocial.com/google_maps"
}

Windsurf~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "scrapersocial-google_maps": {
      "serverUrl": "https://mcp.scrapersocial.com/google_maps",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

Gemini CLI~/.gemini/settings.json

{
  "mcpServers": {
    "scrapersocial-google_maps": {
      "httpUrl": "https://mcp.scrapersocial.com/google_maps",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

Any clientStreamable HTTP · OAuth 2.1 or Bearer

$ npx add-mcp https://mcp.scrapersocial.com/google_maps

One account and one balance across every client and the every-platform hub at mcp.scrapersocial.com.

What it does

What your agent can do with Google Maps

Building a store locator, vetting a neighbourhood for a client, or checking whether a listing’s details match a website: all of it starts with a Maps place, and https://mcp.scrapersocial.com/google_maps gives an MCP client a structured way to find places and read what Google shows about them, so the model works from fields rather than screenshots.

The one capability tool is search: a query such as ” in ” returns matching places at 2 credits each. The rest is reached by path. After a free list_endpoints, call_endpoint can run /v1/google_maps/place, which takes a Maps URL and returns that place’s details for 3 credits, and /v1/google_maps/photos, which takes the same URL and lists the images attached to the listing at 1 credit per image.

A fourth path exists and deserves a plain description. /v1/google_maps/contacts takes a query and returns contact details for the businesses that match, 3 credits per place. It is not wrapped by any tool, so an agent only reaches it by naming the path deliberately. The output can include names, phone numbers and email addresses, which means privacy law applies to what you do with it. Read the acceptable-use section of the terms and the API docs before using it, and don’t use it for unsolicited bulk outreach where that is restricted.

Google Maps is a mapping product, not a social network; here it is treated as public web data, nothing more.

Four jobs it finishes on its own

Shortlist places in an area

Ask for twenty coffee shops near a station and the agent calls search once, 40 credits, and returns names, addresses and ratings it can sort. Follow up on any of them with /v1/google_maps/place for the full record.

Verify a listing against a website

Give the agent a Maps URL and the business's own site. It reads the place with /v1/google_maps/place, compares hours, phone and address, and reports mismatches. Three credits per location makes a 100-location audit a 300-credit job.

Collect photos for a location page

/v1/google_maps/photos returns the images on a listing at 1 credit each. Pair it with place details and the model can draft a venue description with the imagery to hand.

Market research on a category

Run search for the same category across several cities and compare density and ratings. Each city is one call; the credits scale with the number of places you ask for, not the number of cities.

Limits · read before you connect

What this does not do

Written by a person, not generated. If something here is wrong, tell us.

Public listing data only. Nothing here geocodes, routes, draws a map or embeds a widget; Google’s own Platform APIs do those with a licence that permits display. Reviews are not on this spoke; the Google Search server carries them. search and the contacts path both paginate: a page holds 20 places unless you say otherwise, 50 is the most one call returns, and meta.next_cursor continues from there. The contacts path returns personal contact details for business matches and is excluded from the capability tools; you call it by name, and you carry the compliance obligation for how its output is stored and used. Calls are read-only. A search that finds nothing is still billed 1 credit.

Tools

3 tools, same names as the every-platform hub

One does one Google Maps thing each. The last two reach all 4 endpoints by path, so nothing in the catalog is out of an agent's reach.

Full credit table →

Search a platform

search

Keyword search over one platform's public content.

2 credits / place

Reaches the other 3 endpoints

List every Google Maps endpoint

list_endpoints

Browse every Google Maps endpoint, its input and its credit cost. Free, and calls nothing upstream.

free

Call any Google Maps endpoint by path

call_endpoint

Run any Google Maps endpoint by its path, so nothing Google Maps offers is out of reach of an agent.

endpoint's own cost

Pricing

100 free credits is 50 search results.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Calls cost between 1 and 3 credits on Google Maps.

50 search resultssearch · 2 each

Get a free key 100 credits on signup · $5 for 1,000 · full credit table

Prompts

Things to ask once it is connected

Copy one, swap the placeholder, paste it into your client.

Find the 20 highest-rated <category> in <city> and list them with addresses and rating counts.

Read this Google Maps listing and summarise the place: <google maps url>

Compare the opening hours on this Maps listing with the ones on <website>: <google maps url>

Get the photos attached to this place and describe what the venue looks like: <google maps url>

Search Google Maps for "<query>" near <neighbourhood> and tell me which ones have more than 500 reviews.

Questions

Before you connect

How much does a place search cost? #

2 credits per place returned, with 20 back unless you set limit higher, up to 50. A place record is 3 credits, each photo is 1 credit, and a contacts result is 3 credits per place. New accounts start with 100 free credits.

What input does the place endpoint want? #

A Google Maps URL for the listing, passed in the url field of call_endpoint. The same URL works for /v1/google_maps/photos.

Why is there no dedicated place-details tool? #

The capability tools wrap the roles that span many platforms. Place details are specific to Maps, so they sit behind call_endpoint, which list_endpoints will point the agent to. The cost and output are the same either way.

Can I use the contacts path to build a lead list? #

Technically it returns business contact details by query. Whether you may collect and use them depends on the privacy law where you and the contacts are, and on the platform's terms; ScraperSocial's terms require lawful use and the API docs describe the field set. If you're unsure, ask counsel before you run it at volume.

Is this an official Google Maps API? #

It is not. ScraperSocial is independent, unaffiliated with Google, and reads what any visitor can see on a public listing.

Go further

Install https://mcp.scrapersocial.com/google_maps, run a place search with your starter credits to see the field set before you build anything. Pair it with the Google Search spoke when you need reviews too, or use the hub so one connection carries every platform ScraperSocial serves.

Get a free key 100 credits, no card

ScraperSocial is independent and not affiliated with, endorsed by or connected to Google Maps. Publicly available data only.