Google MCP Server

Google Search Console MCP Server for Node.js - connect GSC data to Claude, Cursor and other MCP clients

Local serverstdioPython

What is the Google MCP server?

Connect Google to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Google Search Console MCP Server for Node.js - connect GSC data to Claude, Cursor and other MCP clients. The google mcp server is what makes that connection.

What the server does

A powerful Model Context Protocol (MCP) server that connects Google Search Console data to AI assistants like Claude, Cursor, and other MCP-compatible clients. Get instant access to your website's search performance, keywords, rankings, and more through natural language queries.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Installation — The Installation tool exposed by this server
  • Prerequisites — 1. Google Search Console property with verified ownership 2. Google Cloud Project with Search Console API enabled 3. **Service account
  • Dimensions — The Dimensions tool exposed by this server
  • Metrics — The Metrics tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: GOOGLE_APPLICATION_CREDENTIALS, GSC_SITE_URL, DEBUG. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  1. Google Search Console property with verified ownership 2. Google Cloud Project with Search Console API enabled 3. Service account credentials (JSON file)

Installation

Installation goes through your MCP client rather than a global install: point it at google-search-console-mcp-js on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Google's toolset — Installation, Prerequisites, Dimensions and 1 more — is a fair guide to whether it matches your workflow. It is maintained by sudip358; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Google's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
InstallationThe Installation tool exposed by this server.
Prerequisites1. **Google Search Console property** with verified ownership 2. **Google Cloud Project** with Search Console API enabled 3. **Service account credentials** (JSON file)
DimensionsThe Dimensions tool exposed by this server.
MetricsThe Metrics tool exposed by this server.

How to install the Google MCP server

{
  "mcpServers": {
    "google-search-console-1": {
      "command": "npx",
      "args": ["-y", "google-search-console-mcp-js"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "your-value",
        "GSC_SITE_URL": "your-value",
        "DEBUG": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  1. Google Search Console property with verified ownership 2. Google Cloud Project with Search Console API enabled 3. Service account credentials (JSON file)
VariableDescriptionRequired
GOOGLE_APPLICATION_CREDENTIALSConfiguration value read at startup.Optional
GSC_SITE_URLEndpoint or connection string the server talks to.Yes
DEBUGConfiguration value read at startup.Optional

Example prompts to try

  • Use Google to Installation.
  • Use Google to Prerequisites.
  • Use Google to Dimensions.

Frequently asked questions

It connects Google to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Installation, Prerequisites, Dimensions, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Google directly.