MCP GSC
Google Search Console Insights with Claude AI for SEOs
What is MCP GSC?
MCP GSC is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to google search console insights with claude ai for seos
Google Search Console Insights with Claude AI for SEOs
This server falls under the Marketing & SEO and Analytics categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Google Search Console Insights with Claude AI for SEOs
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-gscConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP GSC
MCP GSC is a Python-based MCP server that gives AI assistants direct access to Google Search Console data, enabling SEO professionals to analyze organic search performance, inspect URL indexing status, compare performance periods, and manage sitemaps entirely through natural language. The server exposes 20 purpose-built tools — from `get_search_analytics` to `batch_url_inspection` — and supports both OAuth and service account authentication, making it suitable for individual analysts and automated reporting pipelines alike.
Prerequisites
- Python 3.10+ and the uv package manager installed (https://astral.sh/uv)
- A Google account with at least one property verified in Google Search Console
- OAuth 2.0 client credentials JSON file downloaded from Google Cloud Console (or a service account JSON key for server-side auth)
- An MCP-compatible client such as Claude Desktop, Cursor, or Codex CLI
Install the uv package manager
uv is the recommended way to run the mcp-search-console Python package without a manual virtual environment setup.
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env
uv --versionSet up Google OAuth credentials
In Google Cloud Console, enable the Google Search Console API for your project, create an OAuth 2.0 Desktop application credential, and download the JSON file to a secure location.
Run the server to authenticate
Execute the server once via uvx to trigger the Google OAuth browser flow and cache your credentials for future headless sessions.
GSC_OAUTH_CLIENT_SECRETS_FILE=/path/to/client_secrets.json uvx mcp-search-consoleConfigure your MCP client
Add the server block to claude_desktop_config.json. Use the full absolute path to uvx (find it with `which uvx`).
{
"mcpServers": {
"gscServer": {
"command": "/Users/yourname/.local/bin/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/client_secrets.json",
"GSC_DATA_STATE": "all",
"GSC_SKIP_OAUTH": "false"
}
}
}
}Verify connection in your AI client
After restarting Claude Desktop, ask it to call `get_capabilities` to list all available tools and confirm the server is connected and authenticated.
MCP GSC Examples
Client configuration
Complete claude_desktop_config.json entry for the MCP GSC server with OAuth authentication and optional settings.
{
"mcpServers": {
"gscServer": {
"command": "/Users/yourname/.local/bin/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/client_secrets.json",
"GSC_DATA_STATE": "all",
"GSC_ALLOW_DESTRUCTIVE": "false",
"GSC_SKIP_OAUTH": "false"
}
}
}
}Prompts to try
SEO analysis prompts that exercise the server's 20 tools across analytics, URL inspection, and sitemap management.
- "Show top 20 queries for mysite.com over the last 30 days, and flag any with CTR below 2%"
- "Check indexing status for https://mysite.com/blog and https://mysite.com/contact"
- "Compare search performance between January and February — which pages improved most?"
- "List all sitemaps for https://example.com and flag any with errors"
- "Get the performance overview for my top GSC property"Troubleshooting MCP GSC
Browser OAuth window does not open or shows an error
Confirm the Google Search Console API is enabled in your Google Cloud project and the OAuth client type is set to 'Desktop application'. Delete cached credentials (usually in ~/.config/gsc/) and re-run to force re-authentication.
Tool returns 'Forbidden' or 'insufficient permissions' errors
The authenticated Google account must be an Owner or Full User on the GSC property. In Search Console, go to Settings > Users and Permissions and verify your account's access level.
GSC_ALLOW_DESTRUCTIVE is not set and sitemap deletion fails
Destructive operations (add/delete sitemaps, remove properties) require setting GSC_ALLOW_DESTRUCTIVE=true in the server environment. Add this to your MCP config env block and restart your client.
Frequently Asked Questions about MCP GSC
What is MCP GSC?
MCP GSC is a Model Context Protocol (MCP) server that google search console insights with claude ai for seos It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP GSC?
Follow the installation instructions on the MCP GSC GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP GSC?
MCP GSC works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP GSC free to use?
Yes, MCP GSC is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP GSC Alternatives — Similar Marketing & SEO Servers
Looking for alternatives to MCP GSC? 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.
Google Search Console
★ 882Connects 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.
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 MCP GSC 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 MCP GSC?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.