Google Search Console
Connects Google Search Console with Claude AI to enable SEO professionals to analyze their SEO data through natural language conversations, providing access to property information, search analytics, URL inspection, and sitemap management.
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 connects google search console with claude ai to enable seo professionals to analyze their seo data through natural language conversations, providing access to property information, search analytics, ...
Connects Google Search Console with Claude AI to enable SEO professionals to analyze their SEO data through natural language conversations, providing access to property information, search analytics, URL inspection, and sitemap management.
This server falls under the Marketing & SEO and Analytics categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connects Google Search Console with Claude AI to enable SEO
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx google-search-console-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Google Search Console
The Google Search Console MCP server connects your Google Search Console properties to AI assistants via the Model Context Protocol, enabling SEO professionals to query search analytics, inspect URLs, manage sitemaps, and compare performance periods using plain English. It exposes 20 tools covering property management, search analytics, URL inspection, and sitemap operations, making it one of the most comprehensive SEO intelligence integrations available for AI clients like Claude Desktop, Cursor, and Codex CLI.
Prerequisites
- Python 3.10+ and the uv package manager installed (https://astral.sh/uv)
- A Google account with at least one verified property in Google Search Console
- OAuth 2.0 client credentials JSON file from Google Cloud Console (for OAuth auth) OR a service account JSON key (for service account auth)
- An MCP-compatible client such as Claude Desktop, Cursor, or Codex CLI
Install the uv package manager
The server is distributed as a Python package and runs best via uv. Install it with the official installer.
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/envCreate OAuth credentials in Google Cloud Console
Go to https://console.cloud.google.com, create a project, enable the Google Search Console API, and create an OAuth 2.0 Desktop client. Download the JSON credentials file and save it to a known path such as ~/gsc_client_secrets.json.
Test the server manually
Run the server once directly to confirm your credentials work and trigger the browser-based OAuth flow on first launch.
GSC_OAUTH_CLIENT_SECRETS_FILE=~/gsc_client_secrets.json uvx mcp-search-consoleAdd the server to your MCP client configuration
Edit claude_desktop_config.json (or the equivalent config for your MCP client) to register the server with the required environment variables.
{
"mcpServers": {
"gscServer": {
"command": "/Users/yourname/.local/bin/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/gsc_client_secrets.json"
}
}
}
}Restart your MCP client and verify connection
Fully quit and reopen Claude Desktop. On first use, a browser window will open for Google OAuth consent. After authorizing, the server will cache credentials and future sessions will be silent.
Google Search Console Examples
Client configuration
Full claude_desktop_config.json entry for the Google Search Console MCP server using OAuth authentication.
{
"mcpServers": {
"gscServer": {
"command": "/Users/yourname/.local/bin/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/gsc_client_secrets.json",
"GSC_DATA_STATE": "all",
"GSC_ALLOW_DESTRUCTIVE": "false"
}
}
}
}Prompts to try
Example prompts demonstrating the 20 tools available through the Google Search Console MCP server.
- "List my GSC properties and identify which has the most indexed pages"
- "Show top 20 queries for mysite.com in the last 30 days; highlight those with CTR below 2%"
- "Check indexing status for these URLs: mysite.com/blog, mysite.com/products"
- "Compare February vs January performance — which queries improved most?"
- "Get a performance overview for https://example.com over the last 90 days"
- "Submit the sitemap at https://mysite.com/sitemap.xml to GSC"Troubleshooting Google Search Console
OAuth browser window does not open or credentials are rejected
Ensure the Google Search Console API is enabled in Google Cloud Console and that the OAuth client type is 'Desktop'. Delete any cached credential files (usually in ~/.config/gsc/) and re-run the server to trigger a fresh OAuth flow.
Server returns empty results or 'property not found' errors
Use `list_properties` to see exactly which properties are accessible to your Google account. Ensure the authorized account is added as an owner or full user on the target property in the real Search Console UI.
'uvx: command not found' when Claude Desktop tries to start the server
Provide the full absolute path to uvx in the command field (e.g., /Users/yourname/.local/bin/uvx). Run `which uvx` in your terminal to find the correct path.
Frequently Asked Questions about Google Search Console
What is Google Search Console?
Google Search Console is a Model Context Protocol (MCP) server that connects google search console with claude ai to enable seo professionals to analyze their seo data through natural language conversations, providing access to property information, search analytics, url inspection, and sitemap management. 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 MIT License license. You can use it freely in both personal and commercial projects.
Google Search Console Alternatives — Similar Marketing & SEO Servers
Looking for alternatives to Google Search Console? Here are other popular marketing & seo servers you can use with Claude, Cursor, and VS Code.
TopRank
★ 2.6kGoogle Ads analysis and operations — read performance, manage keywords, bids, and campaigns.
Open SEO
★ 2.1kOpen source alternative to Semrush and Ahrefs
ASO Skills
★ 1.4kAI agent skills for App Store Optimization (ASO) and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills-compatible AI assistant to help with keyword research, metadata optimiza
Google Meta Ads GA4
★ 994MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude, Cursor, n8n, Windsurf & more. 250+ tools for campaign management, analytics & optimization.
Meta Ads
★ 923A Model Context Protocol server that allows AI models to access, analyze, and manage Meta advertising campaigns, enabling LLMs to retrieve performance data, visualize ad creatives, and provide strategic insights for Facebook and Instagram platforms.
MCP GSC
★ 875Google Search Console Insights with Claude AI for SEOs
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.
Set Up Google Search Console in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.