Start free

Platforms MCP server

MCP server · 4 tools · 5 endpoints

Google Search MCP server

Result pages, Business Profile details, reviews, updates and company ads, handed to your agent as structured JSON.

Get a free key Connect in a minute

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

scrapersocial-google mcp.scrapersocial.com/googleconnected

you

Search Google for "<query>" and tell me whether <mydomain.com> appears in the first page of results.

agent

calls search 2 credits / page

{ "query": "<keywords>" }

server

returns

pages [{ … }] · one per page

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

claude.aiOAuth

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

mcp.scrapersocial.com/google

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

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

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": {
      "url": "https://mcp.scrapersocial.com/google",
      "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",
  "type": "http",
  "url": "https://mcp.scrapersocial.com/google"
}

Windsurf~/.codeium/windsurf/mcp_config.json

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

Gemini CLI~/.gemini/settings.json

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

Any clientStreamable HTTP · OAuth 2.1 or Bearer

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

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 Search

Google isn’t a social network, and this page won’t tell you otherwise. What ScraperSocial does here is treat the public Google surface as data: the results page for a query, and what Google publishes about a business listing. Both are the raw material of local SEO, reputation monitoring and competitor research, and both are easier to work with as JSON than as a browser tab your agent can’t read.

Two capability tools live on https://mcp.scrapersocial.com/google. search returns the results for a query, 2 credits per page returned. get_reviews takes a business URL or handle and returns its public reviews and ratings, 2 credits per review. Three more paths sit behind call_endpoint after a free list_endpoints: /v1/google/business-info for the profile itself (3 credits), /v1/google/business-updates for the posts a business publishes on its listing (3 credits per post), and /v1/google/company-ads for the ads a company is currently running (3 credits per ad).

That is the whole catalogue for this spoke. Maps places, news headlines, shopping listings, trends and finance quotes each live on their own ScraperSocial server with their own paths, because each is a different set of endpoints with different costs. Nothing here touches Search Console or Analytics for properties you own; those are account-scoped and Google’s own APIs are the right tool.

Four jobs it finishes on its own

Rank checking without a browser

Ask which pages come back for a target query and whether your domain is among them. search returns result pages at 2 credits each, so a weekly check across twenty queries costs a predictable 40 credits.

Review monitoring for a listing

Hand get_reviews the business URL and have the agent flag anything under three stars or any review mentioning a named employee. Combine with /v1/google/business-info to confirm the hours and address shown to customers are current.

What a competitor is advertising

/v1/google/company-ads lists the ads a company is running, which tells you what offers and messages they are paying to push. Three credits per ad keeps a quarterly sweep of five competitors well inside a $5 plan.

Local SEO audits

For each client location, pull the profile, the latest updates and the most recent reviews, then let the model write the audit. It is the same three paths every time, so the prompt can be saved and rerun.

Limits · read before you connect

What this does not do

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

Only public results and public listing data; the server never signs in to a Google account and cannot read ad spend, Search Console or Analytics. Per-advertiser ad lookups, the questions-and-answers section of a listing and hotel results are not offered right now; list_endpoints shows only what can serve. Expect 20 items on a list unless you set limit, and never more than 50 in one response; meta carries next_cursor when there is another page. Result pages reflect what Google returned to the request, not a personalised session, so expect differences from your own browser. Even a zero-result query costs 1 credit, the floor on every successful call.

Tools

4 tools, same names as the every-platform hub

Two do one Google Search thing each. The last two reach all 5 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 / page

Read reviews

get_reviews

Public reviews and ratings for a product, business, app or company page.

2 credits / review

Reaches the other 3 endpoints

List every Google Search endpoint

list_endpoints

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

free

Call any Google Search endpoint by path

call_endpoint

Run any Google Search endpoint by its path, so nothing Google Search 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 2 and 3 credits on Google Search.

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.

Search Google for "<query>" and tell me whether <mydomain.com> appears in the first page of results.

Get the latest 50 reviews for this business and summarise the complaints: <google business url>

What ads is <company> currently running on Google? List the headlines and offers.

Pull the Business Profile info for <business name or url> and check the opening hours against this list: <hours>

Show me the recent updates posted on this Google listing and suggest what to post next: <url>

Questions

Before you connect

What does one Google search cost? #

2 credits per result page returned. Reviews are 2 credits each, and the business-info, business-updates and company-ads paths are 3 credits per call or per item. New accounts get 100 credits free, and $5 a month adds 1,000.

Can I get Maps places, news or shopping results from this server? #

Not from this one. Each of those is a separate spoke under mcp.scrapersocial.com with its own paths. Connect the hub if you want all of them behind a single connection.

Why does get_reviews accept a handle as well as a URL? #

Because the catalogue lists its input as url or handle: you can pass the listing URL copied from Google or the identifier the server reports for it. Either resolves to the same business.

Are the results the same as what I see when I search? #

Close, but not identical. Google tailors result pages by location, history and signed-in state. The server returns what Google served to an anonymous request, which is usually what an SEO audit wants anyway.

Does Google endorse or partner with ScraperSocial? #

No. ScraperSocial operates independently, has no affiliation with Google, and returns publicly available data only.

Go further

Wire https://mcp.scrapersocial.com/google into Claude, Cursor or VS Code and run your first rank check on the free credits. When you want news headlines, Maps places and Trends data in the same conversation, the hub serves every ScraperSocial spoke through one URL.

Get a free key 100 credits, no card

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