Google Search Console

v1.0.0Marketing & SEOstable

An MCP server for Google Search Console. Ask Claude questions about your search data and get real answers. 20 tools: quick wins, cannibalisation, content decay, CTR benchmarking, alerting, indexing API, and more.

suganthans-gsc-mcpmcpai-integration
Share:
66
Stars
0
Downloads
0
Weekly
0/5

What is Google Search Console?

Google Search Console is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for google search console. ask claude questions about your search data and get real answers. 20 tools: quick wins, cannibalisation, content decay, ctr benchmarking, alerting, indexing api, ...

An MCP server for Google Search Console. Ask Claude questions about your search data and get real answers. 20 tools: quick wins, cannibalisation, content decay, CTR benchmarking, alerting, indexing API, and more.

This server falls under the Marketing & SEO and Analytics categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP server for Google Search Console. Ask Claude question

Use Cases

Analyze search performance and CTR data.
Identify content decay and cannibalization issues.
Set up SEO alerts and monitor indexing status.
LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx suganthans-gsc-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Google Search Console

This MCP server connects AI assistants directly to Google Search Console, exposing 20 specialized SEO analysis tools that let you ask natural-language questions about your site's search performance and get real data-backed answers. Tools cover quick wins identification, keyword cannibalization detection, content decay analysis, CTR benchmarking against industry norms, URL inspection, indexing submission, and multi-site dashboards. It supports both OAuth 2.0 and service account authentication, making it suitable for both individual site owners and agencies managing multiple properties.

Prerequisites

  • Node.js 18 or later installed on your system
  • A Google account with your site verified in Google Search Console
  • Google Cloud project with the Search Console API enabled, plus either an OAuth 2.0 client secrets JSON file or a service account key JSON file
  • An MCP-compatible client such as Claude Desktop
  • Git to clone the repository
1

Clone the repository and build

Clone the GSC MCP repository and compile the TypeScript source to produce the dist/index.js entry point.

git clone https://github.com/Suganthan-Mohanadasan/Suganthans-GSC-MCP.git
cd Suganthans-GSC-MCP
npm install
npm run build
2

Set up Google Cloud credentials

In the Google Cloud Console, enable the Google Search Console API for your project. Then either create OAuth 2.0 credentials (for personal use) or a service account with Search Console read access (for automated/agency use). Download the JSON key file.

3

Configure Claude Desktop with OAuth authentication

Add the GSC server to your claude_desktop_config.json using OAuth mode. GSC_SITE_URL must match your verified property in Search Console (use sc-domain: prefix for domain properties).

{
  "mcpServers": {
    "gsc": {
      "command": "node",
      "args": ["/path/to/Suganthans-GSC-MCP/dist/index.js"],
      "env": {
        "GSC_AUTH_MODE": "oauth",
        "GSC_OAUTH_SECRETS_FILE": "/path/to/client_secrets.json",
        "GSC_SITE_URL": "sc-domain:yoursite.com"
      }
    }
  }
}
4

Or configure with a service account

For automated access without browser login prompts, use service account authentication with the key file downloaded from Google Cloud.

{
  "mcpServers": {
    "gsc": {
      "command": "node",
      "args": ["/path/to/Suganthans-GSC-MCP/dist/index.js"],
      "env": {
        "GSC_KEY_FILE": "/path/to/service-account.json",
        "GSC_SITE_URL": "sc-domain:yoursite.com"
      }
    }
  }
}
5

Restart Claude Desktop and run a test query

Restart Claude Desktop and ask it for a site snapshot or quick wins. This confirms authentication worked and the 20 GSC tools are available.

Google Search Console Examples

Client configuration

Claude Desktop config using service account authentication for headless/automated GSC access.

{
  "mcpServers": {
    "gsc": {
      "command": "node",
      "args": ["/Users/yourname/Suganthans-GSC-MCP/dist/index.js"],
      "env": {
        "GSC_KEY_FILE": "/Users/yourname/.credentials/gsc-service-account.json",
        "GSC_SITE_URL": "sc-domain:yoursite.com"
      }
    }
  }
}

Prompts to try

Natural-language SEO analysis questions to ask Claude once the GSC MCP server is connected.

- "What are my quick win keywords — high impressions, low CTR — for this month?"
- "Which pages have lost significant traffic in the past 30 days and why?"
- "Check for keyword cannibalization on my blog"
- "How does my CTR compare to benchmarks for my top queries?"
- "Submit this URL for indexing: https://yoursite.com/new-page"
- "Generate a full search performance report for the past 90 days"

Troubleshooting Google Search Console

Authentication fails with 'access denied' or 403 error

For service accounts, ensure the service account email has been added as a user in Google Search Console (Settings → Users and permissions) with at least Restricted access. For OAuth, complete the browser consent flow on first run and ensure the client secrets file path is correct.

GSC_SITE_URL does not match any verified property

The site URL format must exactly match what is shown in Google Search Console. Domain properties use the 'sc-domain:' prefix (e.g., sc-domain:example.com). URL-prefix properties use the full URL with trailing slash (e.g., https://example.com/). Check your verified properties at search.google.com/search-console.

npm run build fails with TypeScript errors

Ensure you are using Node.js 18 or later ('node --version'). Run 'npm install' first to install all dependencies including the TypeScript compiler. If specific type errors appear, check that your Node.js version matches what the project expects in its package.json engines field.

Frequently Asked Questions about Google Search Console

What is Google Search Console?

Google Search Console is a Model Context Protocol (MCP) server that mcp server for google search console. ask claude questions about your search data and get real answers. 20 tools: quick wins, cannibalisation, content decay, ctr benchmarking, alerting, indexing api, and more. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Google Search Console?

Follow the installation instructions on the Google Search Console GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Google Search Console?

Google Search Console works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Google Search Console free to use?

Yes, Google Search Console is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Marketing & SEO MCP Servers

Explore all marketing & seo servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "suganthans-gsc-mcp": { "command": "npx", "args": ["-y", "suganthans-gsc-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Google Search Console?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides