Google Search Console MCP Server

What is Google Search Console MCP Server?

This MCP server allows Claude AI (via the Claude Desktop app) to interact with the Google Search Console API. It enables querying search performance data, inspecting URLs, checking indexing status, and managing sitemaps directly from the Claude chat.

How to use Google Search Console MCP Server?

Set up a Python 3.11+ virtual environment, install dependencies with pip install -e ., and place a downloaded credentials.json from Google Cloud (OAuth Desktop app) in the project root. Add the server to the Claude Desktop config (claude_desktop_config.json) with the absolute path to the virtual environment’s python3 binary and -m main as arguments. On first tool use, your browser will open for Google OAuth authentication, creating a token.json file.

Key features of Google Search Console MCP Server

• List accessible sites/properties in Search Console.
• Fetch search performance data (clicks, impressions, CTR, position).
• Filter and group data by queries, pages, countries, devices.
• Inspect any URL’s indexing status and request indexing.
• View and manage submitted sitemaps for a site.

Use cases of Google Search Console MCP Server

• "List my sites in Google Search Console."
• "Get the search performance for example.com for the last 7 days, broken down by query."
• "Inspect the URL https://example.com/my-page on site example.com."
• "Are there any mobile usability issues for example.com?"
• "Submit https://example.com/new-article for indexing on site example.com."

FAQ from Google Search Console MCP Server

What prerequisites are needed?

Python 3.11+, pip, a Google Account with Search Console access, and the Claude Desktop app installed and running.

Where are credentials stored?

OAuth client ID is stored in a credentials.json file in the project root. After first authorization, an access token.json file is created – both should be kept private and not committed.

What data can I query?

You can query search analytics (clicks, impressions, CTR, position), inspect individual URLs, list sites, and manage sitemaps. Index coverage details and crawl errors beyond the URL Inspection API are not exposed.

How does authentication work?

The server uses Google OAuth 2.0 with a "Desktop app" OAuth client. On first tool call, your browser opens to log in and grant permissions; subsequent calls reuse the stored token.json.

What transport does the server use?

The server uses stdio transport, listening for JSON-RPC messages on standard input/output, and logs are printed to standard error.