Connecting Google Search Console to Claude Code with MCP

Description and use

Integrating Google Search Console with Claude Code via the mcp-gsc MCP server enables direct analysis of search data within the development environment. This eliminates manual CSV exports and spreadsheet work, allowing the AI assistant to suggest code changes based on real SEO metrics.

Problem

Analyzing Google Search Console (GSC) data requires switching between GSC, spreadsheets, and the codebase, creating friction in the SEO optimization workflow.

Outcome

The integration eliminates manual data transfer, allowing the AI assistant to access real-time search data to investigate pages and suggest precise code changes, streamlining the SEO-to-code loop.

Workflow

• Create a dedicated project in Google Cloud Console.
• Enable the Google Search Console API.
• Configure OAuth consent screen (External, Testing) and add test users.
• Create an OAuth 2.0 Client ID for Desktop app and download the JSON credentials.
• Install 'uv' and verify 'uvx' availability.
• Add the mcp-gsc server to Claude Code configuration using absolute paths for uvx and credentials.
• Authorize the connection via browser OAuth flow.
• Verify connection by listing properties and checking authentication status.
• Use specific prompts to analyze performance, diagnose low CTR, compare periods, or check indexing.

Evidence

My SEO workflow changed from: GSC → CSV export → spreadsheet → codebase to: Search data → opportunity → page → code change → measurement

Source

The biggest benefit is not generating more SEO content. It is giving the coding assistant real search data so it can investigate the correct page before making a change.

Source