How I Connected Google Search Console to Claude Code with MCP

A developer connected Google Search Console to Claude Code using Amin Forou's open-source mcp-gsc server, enabling natural language queries for SEO analysis. The integration uses MCP over stdio and OAuth 2.0 to access Search Console data, with tools for performance analysis, URL inspection, and sitemap management. The setup requires a Google Cloud project, OAuth credentials, and the uvx package runner, with a note about token expiration for external apps in Testing mode.

I wanted to analyze Google Search Console data without jumping between GSC, spreadsheets, and my codebase. So I connected GSC to Claude Code using Amin Forou's open-source mcp-gsc server https://github.com/AminForou/mcp-gsc . Now I can ask: Claude retrieves the relevant data, analyzes it alongside my code, and helps me decide what to change. Claude Code ↓ MCP over stdio mcp-gsc running locally ↓ OAuth 2.0 Google Search Console API The MCP server converts Search Console operations into tools Claude can call. It supports performance analysis, URL inspection, sitemap management, period comparisons, and property discovery. I used OAuth so the server could access the same GSC properties as my Google account. Open the Google Cloud Console https://console.cloud.google.com/ and create a dedicated project. Then: The authorized Google account must already have access to the Search Console property. The server requests this scope: https://www.googleapis.com/auth/webmasters This is the read/write Search Console scope. Destructive mcp-gsc operations remain disabled unless GSC ALLOW DESTRUCTIVE=true is explicitly set. Important: for an external app in Testing, Google normally expires the authorization and refresh token after seven days. If authentication suddenly stops, run the reauthentication tool and approve access again. In Google Auth Platform → Clients : Example: /Users/yourname/Documents/credentials/gsc-client-secrets.json Never commit this file to Git. The simplest method uses uvx , which runs the package in an isolated Python environment. Install uv using its official installation guide https://docs.astral.sh/uv/getting-started/installation/ , then verify it: uv --version uvx --version which uvx Keep the full path returned by which uvx . Claude Code may not inherit your terminal's PATH , so using only uvx can cause a spawn uvx ENOENT error. Replace the example paths with absolute paths from your machine: claude mcp add-json --scope user gscServer '{ "type": "stdio", "command": "/Users/yourname/.local/bin/uvx", "args": "mcp-search-console" , "env": { "GSC OAUTH CLIENT SECRETS FILE": "/Users/yourname/Documents/credentials/gsc-client-secrets.json" } }' I used user scope so the integration was available across my local projects without committing credential paths to a repository. Verify the configuration: claude mcp list claude mcp get gscServer Start Claude Code and ask: Call the GSC get capabilities tool and report the authentication status. The first request opens Google's OAuth flow in your browser. Sign in with the test-user account and approve access. Then ask: List every Search Console property I can access and show its exact identifier. Use the identifier returned by the API. Search Console has two formats: Domain property: sc-domain:example.com URL-prefix property: https://www.example.com/ The protocol, hostname, and trailing slash must match exactly for URL-prefix properties. The server exposes tools including: get performance overview get search analytics get advanced search analytics compare search periods get search by page query inspect url enhanced batch url inspection check indexing issues list sitemaps enhanced reauthenticate For recent dashboard-like data, keep the default GSC DATA STATE=all . For stable reporting with a short delay, use GSC DATA STATE=final . For sc-domain:example.com, find non-branded queries with at least 500 impressions and positions from 11 to 20 in the last 28 days. Group them by ranking page and recommend whether to update an existing page or create a new one. Find pages ranking in positions 1 to 10 with at least 1,000 impressions and CTR below 2%. Show their leading queries and suggest accurate title improvements. Compare the latest 28 complete days with the previous 28 days. Separate changes caused by impressions, CTR, and position. Show the ten biggest winning and losing pages. Inspect the ten highest-click landing pages. Flag canonical mismatches, robots restrictions, crawl failures, and pages missing from Google's index. Authentication fails after seven days: Your external OAuth app is still in Testing. Call reauthenticate and approve access again. spawn uvx ENOENT: Use the complete path returned by which uvx . Credentials file not found: Use an absolute path in GSC OAUTH CLIENT SECRETS FILE . Property returns 404: Run list properties and copy the exact sc-domain: or URL-prefix value. No MCP tools appear: Check claude mcp list . Manual repository installations also require Python 3.11 or newer. My SEO workflow changed from: GSC → CSV export → spreadsheet → codebase to: Search data → opportunity → page → code change → measurement 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. Disclosure: I used AI to help edit this article. The setup is based on my own implementation and was manually verified.