Google Search Console MCP Server

A Model Context Protocol (MCP) server that provides programmatic access to Google Search Console API data through Claude Code and Cursor.

Quick Start

New to this MCP server? Jump to Step-by-Step Setup Guide for complete instructions.

Features

• 🔍 List Sites - Get all Search Console properties you have access to
• 📊 Search Analytics - Query search performance data with flexible filtering
• 🗺️ Sitemap Information - Retrieve sitemap status and indexing statistics
• 🔎 URL Inspection - Check detailed indexing status of specific URLs
• 📤 Submit URL for Indexing - Request Google to index or remove URLs
• 📈 Compare Periods - Compare search performance between two time periods
• 🛡️ Robust Error Handling - Detailed error messages with actionable guidance
• 🔄 Automatic Retry Logic - Handles rate limits and transient failures
• ✅ Input Validation - Validates all parameters before API calls

Prerequisites

Before using this MCP server, you need:

1. Google Search Console

• Site registered in Search Console
• Site ownership verified
• Access to the Search Console property you want to query

2. Google Cloud Platform (GCP)

• A GCP project (free tier is sufficient)
• Google Search Console API enabled
• OAuth 2.0 Client ID credentials (Desktop app type)
• (Optional) Indexing API enabled if you want to use submit_url_for_indexing

💡 Note: You only need to set up GCP once. The CLIENT_ID and CLIENT_SECRET are reusable across multiple sites in your Search Console.

Setup

1. Configure Claude Code

Create .mcp.json in your project root:

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "-p", "google-search-console-mcp-server", "google-search-console-mcp"],
      "env": {
        "GOOGLE_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
        "GOOGLE_CLIENT_SECRET": "your-client-secret",
        "GOOGLE_REFRESH_TOKEN": "your-refresh-token"
      }
    }
  }
}

⚠️ Important: The args must include all three parts:

1. "-y" - Auto-confirm npx prompt
2. "-p", "google-search-console-mcp-server" - Package name
3. "google-search-console-mcp" - Executable name (different from package name!)

💡 Note: GOOGLE_REDIRECT_URI defaults to http://localhost:8080 and doesn't need to be specified unless you want to use a different port.

2. Get Google OAuth Credentials

💡 Tip: You can use an existing OAuth 2.0 Client ID from other services (Supabase, Firebase, etc.) or create a new one.

1. Go to Google Cloud Console
2. Create or select a project
3. Enable APIs:
   • Navigate to "APIs & Services" → "Enable APIs and Services"
   • Search and enable "Google Search Console API"
   • (Optional) Enable "Indexing API" if you want to use submit_url_for_indexing
4. Create or use existing OAuth 2.0 Client ID:
   • Go to "APIs & Services" → "Credentials"
   • Option A: Use existing OAuth 2.0 Client (skip to step 5)
   • Option B: Create new → "OAuth 2.0 Client ID" → Application type: Desktop app
5. Configure Authorized redirect URIs:
   • Click on the OAuth 2.0 Client ID
   • Under "Authorized redirect URIs", click "Add URI"
   • Add: http://localhost:8080 (no trailing slash!)
   • Click "Save"
6. ⚠️ IMPORTANT: Add test users (if OAuth consent screen is in Testing mode):
   • Go to "OAuth consent screen"
   • Check the "Publishing status" - if it shows "Testing":
   • Scroll to "Test users" section
   • Click "+ ADD USERS"
   • Add your Google account email (the one you'll use to authenticate)
   • Click "Save"
   • Without this step, you'll get access_denied errors!

💾 Save your credentials: Copy the CLIENT_ID and CLIENT_SECRET. You'll need them in the next step.

3. Get Refresh Token

Run the interactive setup comma

... View full README on GitHub