Google Search Console MCP Server

What is Google Search Console MCP Server?

This server integrates Google Search Console (GSC) data with Claude Desktop via the Model Context Protocol (MCP). It allows users to compare time periods, generate visual reports, and analyze SEO metrics like click-through rates, impressions, and ranking shifts.

How to use Google Search Console MCP Server?

Generate a Google Cloud service account JSON key and add it to your GSC property. Then clone the repository, create a Python virtual environment with uv, install dependencies, and run mcp install server.py -v GOOGLE_APPLICATION_CREDENTIALS=<path to JSON> . Restart Claude Desktop to see five new tools and start querying your search analytics.

Key features of Google Search Console MCP Server

• Lists all verified sites in your Google Search Console account
• Queries search analytics with dimensions (query, page, device, country, date)
• Compares two time periods for SEO performance changes
• Identifies top performing pages by clicks, impressions, CTR, or position
• Provides search trend data grouped by day, week, or month

Use cases of Google Search Console MCP Server

• Compare search performance between last month and the previous month
• Identify keywords with high impressions but low CTR for optimization
• Create visual reports (bar charts, line graphs) of SEO data
• Find pages that dropped in rankings or new keywords ranking in last 30 days
• Analyze seasonal trends and prioritize optimization opportunities

FAQ from Google Search Console MCP Server

What tools does the server provide?

Five tools: list_sites, query_search_analytics, compare_time_periods, get_top_performing_content, and get_search_trends.

What credentials are required?

A Google Cloud service account JSON key with the Search Console API enabled and the service account added as a user in Google Search Console.

What are the runtime dependencies?

Python, pip, uv, and optionally Git. The server runs locally via Claude Desktop.

How do I install the server?

Clone the repo, create a virtual environment with uv venv, run uv sync, then mcp install server.py -v GOOGLE_APPLICATION_CREDENTIALS=<path>. Restart Claude Desktop.

What if the tools don't appear in Claude Desktop?

Restart Claude Desktop (end the process in Task Manager/Activity Monitor) and wait a few minutes. Also verify the JSON credentials path is correct and accessible.