mcpField
S
serpgrab: Google Search and Maps

serpgrab: Google Search and Maps

Remote
serpgrab.comSearch0Updated 4d ago

About serpgrab: Google Search and Maps

serpgrab is a hosted MCP server that returns real-time Google Search and Google Maps results for AI agents. Its tools include search features such as AI Overviews and People also ask, as well as detailed place listings, formatted as compact text for model context.

Key features

  1. 01Retrieve Google web search results
  2. 02Include AI Overview and related result modules
  3. 03Search Google Maps businesses and places
  4. 04Filter searches by location, language, and time
  5. 05Return compact text for model context

Use cases

  1. 01Research current web results for a query
  2. 02Find local businesses and review place details
  3. 03Limit results to a region or recent time period

MCP support

Exposes the `google_search` and `google_maps_search` tools through a hosted Streamable HTTP MCP server. Clients connect to its URL and provide an API key to run searches.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.serpgrab.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://api.serpgrab.com/mcpAuth required
Streamable HTTPhttps://google-serp-search-results-json.p.rapidapi.com/mcpAuth required

Tools

Details

From the project README

serpgrab MCP server

A hosted MCP server that gives AI agents real-time Google search and Google Maps results, from serpgrab. There is nothing to install: add one URL to your MCP client.

https://api.serpgrab.com/mcp

This repository holds the setup docs and client config examples. The server itself runs on our infrastructure and is not open source. It is listed in the official MCP registry as com.serpgrab/google-search.

Tools

  • google_search: Google web results (title, URL, date, snippet), plus the AI Overview, answer box, knowledge panel, local pack, ads and "People also ask" when Google shows them.
  • google_maps_search: businesses and places from Google Maps, 20 a page, with rating, reviews, price, address, phone, hours, website, coordinates and place_id.

Results come back as compact text written for a model's context, not raw JSON.

google_search
ArgumentDefault
query(required)The search, as typed into Google
pages1Result pages to read, 1-3 (about 10 results each)
countryusTwo-letter country Google searches from (gl)
languageenInterface language (hl)
locationSearch as if from a place, e.g. Austin, Texas, United States
timehour, day, week, month or year: only recent results
google_maps_search
ArgumentDefault
query(required)What to look for, e.g. pizza in austin tx
llMap position, @latitude,longitude,zoomz, e.g. @30.2672,-97.7431,14z
page1Results page, 20 places each
countryusTwo-letter country (gl)
languageenInterface language (hl)

Get a key

Free: 250 searches a month, email signup, no card: https://serpgrab.com/#signup

Connecting and listing the tools work without a key; running a tool needs one. Each results page the agent reads is one search.

Setup

Replace YOUR_KEY with your serpgrab key.

Claude Code
claude mcp add --transport http serpgrab https://api.serpgrab.com/mcp \
  --header "X-API-Key: YOUR_KEY"
Cursor

In ~/.cursor/mcp.json, or .cursor/mcp.json in a project:

{
  "mcpServers": {
    "serpgrab": {
      "url": "https://api.serpgrab.com/mcp",
      "headers": { "X-API-Key": "YOUR_KEY" }
    }
  }
}
VS Code

In .vscode/mcp.json, or run MCP: Open User Configuration:

{
  "servers": {
    "serpgrab": {
      "type": "http",
      "url": "https://api.serpgrab.com/mcp",
      "headers": { "X-API-Key": "YOUR_KEY" }
    }
  }
}
Windsurf

In Cascade's MCP menu, choose Open MCP config file and add:

{
  "mcpServers": {
    "serpgrab": {
      "serverUrl": "https://api.serpgrab.com/mcp",
      "headers": { "X-API-Key": "YOUR_KEY" }
    }
  }
}
Codex

In ~/.codex/config.toml:

[mcp_servers.serpgrab]
url = "https://api.serpgrab.com/mcp"
http_headers = { "X-API-Key" = "YOUR_KEY" }
Claude.ai, Claude Desktop, ChatGPT and other clients that only take a URL

Put the key in the URL and choose no authentication:

https://api.serpgrab.com/mcp?api_key=YOUR_KEY
  • Claude.ai and Claude Desktop: Settings › Connectors › Add custom connector.
  • ChatGPT: turn on developer mode, then Settings › Connectors › Create.

We don't log keys sent in the URL, but the client stores the URL with its settings, so keep it as private as the key.

Clients that only speak stdio

Connect through mcp-remote:

{
  "mcpServers": {
    "serpgrab": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.serpgrab.com/mcp", "--header", "X-API-Key:YOUR_KEY"]
    }
  }
}

Pro plan on RapidAPI

Pro is $15 a month for 5,000 searches, on RapidAPI. Subscribers connect through RapidAPI's gateway with their RapidAPI key:

claude mcp add --transport http serpgrab https://google-serp-search-results-json.p.rapidapi.com/mcp \
  --header "X-RapidAPI-Key: YOUR_RAPIDAPI_KEY" \
  --header "X-RapidAPI-Host: google-serp-search-results-json.p.rapidapi.com"

RapidAPI counts every request to the server, so connecting uses about three of your plan's requests, and each tool call one more.

Transport

Streamable HTTP, stateless, with JSON replies (no SSE stream). Only POST is used.

The API underneath

serpgrab returns Google results in SerpApi's JSON format, so the same key also works for your own code: see the migration guide and the OpenAPI spec.

Help

Setup page: https://serpgrab.com/mcp. Questions or a tool you'd like: [email protected].

License

The docs and examples in this repository are MIT licensed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.