serpgrab MCP

A hosted MCP server that enables AI agents to perform real-time Google Search and Google Maps queries. It provides tools to retrieve search results including AI Overviews, answer boxes, and local packs, as well as business details from Google Maps, returning readable text to optimize context usage.

Visit serpgrab

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by serpgrab

You need:Get a free keyReplace YOUR_KEY with your serpgrab key

MCP endpoint (Streamable HTTP)

https://api.serpgrab.com/mcp

Vendor documentation

What you can do with it

Perform real-time Google searches with filters for country, language, and time range
Retrieve Google Maps business details including ratings, hours, and coordinates
Access AI Overview, answer boxes, and People Also Ask data in search results

Source and maintenance

Vendor evidenceRegistry 0.1.2

mcp-registry: com.serpgrab/google-search@0.1.2 Source repository Project website

Maintenance checked: Nov 1, 2026, 6:38 AM UTC

Protocol and capabilities

Server: serpgrab 0.1.2
MCP protocol: 2025-06-18
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Tools

2 advertised

google_search — Google search

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

Real-time Google web results: title, URL, date and snippet for each result, plus the AI Overview, answer box, knowledge panel, local pack, ads and "People also ask" when Google shows them. Question-style queries ("how do I...", "what is...") usually get an AI Overview. Each page read is one billed search, so use pages=1 unless you need more. Usually 2-6 s per page.

google_search input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "time": {
      "enum": [
        "hour",
        "day",
        "week",
        "month",
        "year"
      ],
      "type": "string",
      "description": "Only results from the past hour, day, week, month or year."
    },
    "pages": {
      "type": "integer",
      "maximum": 3,
      "minimum": 1,
      "description": "Result pages to read (about 10 results each), 1-3. Default 1."
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "The search, as typed into Google."
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$",
      "description": "Two-letter country code Google searches from (gl), e.g. \"us\", \"gb\", \"de\". Default \"us\"."
    },
    "language": {
      "type": "string",
      "maxLength": 7,
      "minLength": 2,
      "description": "Interface language (hl), e.g. \"en\", \"de\", \"pt-BR\". Default \"en\"."
    },
    "location": {
      "type": "string",
      "description": "Search as if from this place, e.g. \"Austin, Texas, United States\". Leave out for a country-wide search."
    }
  }
}

google_search annotations

{
  "readOnlyHint": true,
  "openWorldHint": true
}

google_maps_search — Google Maps search

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

Businesses and places from Google Maps, 20 per page: name, type, rating and review count, price, address, phone, hours, website, coordinates and place_id. Put the place in the query ("plumber in denver co") or pass ll. Each page is one billed search.

google_maps_search input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "ll": {
      "type": "string",
      "pattern": "^@-?\\d{1,2}(\\.\\d+)?,-?\\d{1,3}(\\.\\d+)?,\\d{1,2}(\\.\\d+)?z$",
      "description": "Map position as \"@latitude,longitude,zoomz\", e.g. \"@30.2672,-97.7431,14z\"."
    },
    "page": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "Results page, 20 places each. Default 1."
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "What to look for, e.g. \"pizza in austin tx\"."
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$",
      "description": "Two-letter country code Google searches from (gl), e.g. \"us\", \"gb\", \"de\". Default \"us\"."
    },
    "language": {
      "type": "string",
      "maxLength": 7,
      "minLength": 2,
      "description": "Interface language (hl), e.g. \"en\", \"de\", \"pt-BR\". Default \"en\"."
    }
  }
}

google_maps_search annotations

{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 1014 ms
95th percentile latency: 1014 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 7:03 AM UTC · probe · passed · 1014 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http serpgrab-mcp https://api.serpgrab.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add serpgrab-mcp --url https://api.serpgrab.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable serpgrab-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "serpgrab-mcp": {
      "url": "https://api.serpgrab.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "serpgrab-mcp": {
      "type": "streamableHttp",
      "url": "https://api.serpgrab.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start serpgrab-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "serpgrab-mcp": {
      "type": "http",
      "url": "https://api.serpgrab.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http serpgrab-mcp https://api.serpgrab.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "serpgrab-mcp": {
      "url": "https://api.serpgrab.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "serpgrab-mcp": {
      "serverUrl": "https://api.serpgrab.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like serpgrab MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,073

Do you run serpgrab MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing