Connect Google Search Console to Claude

If you manage SEO for a site, you've probably opened Search Console, squinted at a table, and wished you could just ask it a question. Now you can — search-console-mcp-server is an open-source MCP server that connects your real Search Console data straight into Claude, so you can ask things like "which pages lost the most clicks this month" and get an answer pulled from your actual numbers, not a guess.

This guide covers the full setup, in order, plus the first few things worth asking once it's connected.

Why connect Search Console to Claude at all

Search Console has the data. It doesn't have the reasoning. You can see that a page's clicks dropped 40% in the UI, but you still have to cross-reference query changes, check if a competitor started ranking, and figure out whether it's a content problem or an indexing problem — by hand, across multiple tabs.

An MCP server hands that same data to an LLM that can already reason about SEO. Claude can pull the real numbers, compare periods, cross-reference queries against pages, and tell you what's actually going on — with your data, not a generic answer.

The catch with most "AI + Search Console" tools is the setup: create a Google Cloud project, enable the Search Console API, generate OAuth credentials, download a JSON key, wire it into some config. That's 20+ minutes before you've asked a single question. search-console-mcp-server skips all of it.

The 30-second install

You need Node.js installed (most developers already have it — check with node -v). That's the only prerequisite.

Step 1: Sign in.

npx search-console-mcp-server login

Your browser opens, you pick your Google account, you approve read-only access to Search Console. That's it — no Google Cloud console, no API key, no service-account JSON file. Tokens are issued by Google straight to your machine and saved to ~/.search-console-mcp/.

Step 2: Add it to Claude.

If you're using Claude Code:

claude mcp add gsc -- npx -y search-console-mcp-server

If you're using Claude Desktop, open claude_desktop_config.json (on macOS: ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows: %APPDATA%\Claude\claude_desktop_config.json) and add:

{
  "mcpServers": {
    "gsc": {
      "command": "npx",
      "args": ["-y", "search-console-mcp-server"]
    }
  }
}

Restart Claude Desktop. That's the whole setup — from an empty terminal to a working connection in well under a minute.

Using Cursor, Windsurf, or VS Code instead? The config file location and JSON key name differ slightly per client — see the full per-client setup guides for exact paths.

The first 3 prompts to run

For copyable research prompts and a checklist for reviewing the output, see Claude for SEO: four workflows using real Search Console data.

Don't start by exploring. Start with these three — they're the fastest way to see whether anything on your site needs attention right now.

1. "Run a full SEO checkup and give me the top 3 moves."

Ask Claude to list your properties, select your site, and compare the last 28 complete days with the previous 28 by page and query. Have it state the date ranges, show the evidence, and give you up to three actions. The server supplies data tools; the analysis comes from your assistant, and may need several tool calls.

2. "Which queries sit at position 5–15 with real impressions? What's the fix for each page?"

This produces a shortlist to investigate. Average position alone does not establish an easy win: check search intent, the competing results, query volume, and whether the landing page can satisfy the query. Ask Claude to flag sparse data and separate supported actions from ideas that need more research.

3. "Compare this month vs last month, by page. What fell, and why?"

Ask for equal, complete date windows and consistent search type, country, and device filters. Claude can compare the changes and identify where further investigation is needed. Lower impressions do not by themselves prove an indexing issue, and lower CTR does not prove a title problem. Google's traffic-drop guidance covers several possible causes.

What the output actually looks like

Here is an illustrative answer format, not a customer result:

/blog/pricing-guide lost 340 clicks compared with the previous 28 days. Page impressions were similar, but CTR fell from 4.2% to 2.1%. Next, compare the leading queries by device and inspect the current results before changing the title. The aggregate numbers do not establish the cause.

A useful response makes its evidence and uncertainty visible. Search Console does not tell Claude which competitor replaced you; that requires separate results-page research. You still make the actual edit — the MCP reads Search Console, it does not touch your site.

Limits, honestly

This connects Search Console — not Google Analytics, not your CMS, not your backlink profile. It sees clicks, impressions, position, CTR, URL inspection status, and sitemaps: exactly what Search Console itself exposes, no more. Read-only means it also can't submit URLs for indexing or fix anything for you; every fix ships as advice you paste into your CMS yourself.

It's also a one-time ask-and-answer tool. It only has the data it can pull in the moment you ask, and it only checks anything when you open a chat and ask it to. If you close your laptop for two weeks, nothing happens on your site's behalf during that time — the server doesn't run when you're not asking it something.

When a dedicated SEO workspace helps

Keep using the MCP if your existing assistant is where you want to do your research. You do not need to buy Percy to keep accessing your Search Console data through it.

Percy gives that work a dedicated home: chat about a connected site, ask follow-up questions, draft a page change, and save a recommendation as an action. Return to the same conversation when you are ready to implement it. Its action workflow can check that a change landed and follow subsequent performance; changes in traffic alone do not prove that the edit caused them.

Try Percy with your site if you want that workspace. It uses a separate Google connection and does not import your local MCP credentials. There is a 7-day trial with no credit card required, followed by plans from $29/month. Trial usage limits apply. For a comparison of other workflows, see our guide to choosing an AI SEO tool.