Better Google Search Console MCP Server

Better Search Console

Quick Navigation

Why this exists | Quick start | Tools | Insight types | Data retention | Custom SQL | Development | Troubleshooting

Why This Exists

Every SEO tool that connects to an LLM has the same problem: the Google Search Console API returns 1,000 rows per request, your context window fills up fast, and you end up asking the model to reason about a tiny fraction of your data. The answers sound plausible but they're built on incomplete information.

This MCP server takes a different approach. It downloads your entire Search Console dataset into a local SQLite database, then gives Claude pre-built SQL queries for every standard SEO analysis type. Claude never sees the raw data. It sees query results: the top 50 declining pages, the queries ranking 5-20 with high impressions, the device breakdown for a specific URL pattern. Precise answers from complete data, using a few hundred tokens instead of tens of thousands.

What you get

One database per GSC property, synced in the background with full pagination (no row limits). Sixteen pre-built insight queries covering the things SEOs check repeatedly. Custom SQL for everything else. Automatic data retention that prunes low-value rows after each sync to keep databases from growing without bound. The data stays on your machine and the queries run in milliseconds.

Quick Start

Step 1: Set Up Google Credentials

You need a Google Cloud service account with Search Console API access. Here is how to create one from scratch.

Create a Google Cloud project and enable the API

1. Go to the Google Cloud Console
2. Create a new project (or select an existing one)
3. Go to APIs and Services > Library
4. Search for Google Search Console API and click Enable

Create a service account

1. Go to APIs and Services > Credentials
2. Click Create Credentials > Service account
3. Give it a name (e.g. search-console-mcp) and click Create and Continue
4. Skip the optional role and user access steps, click Done
5. Click on the service account you just created
6. Go to the Keys tab
7. Click Add Key > Create new key > JSON
8. Save the downloaded JSON file somewhere safe (e.g. ~/credentials/gsc-service-account.json)

For full details on creating credentials, see the Google Workspace credentials guide.

Grant the service account access to Search Console

1. Open the JSON key file and copy the client_email value (it looks like name@project.iam.gserviceaccount.com)
2. Go to Google Search Console
3. Select a property
4. Go to Settings > Users and permissions > Add user
5. Paste the service account email and set permission to Full
6. Repeat for each property you want to access

Step 2: Add to Claude Desktop

Add this to your Claude Desktop config file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "better-search-console": {
      "command": "npx",
      "args": ["-y", "@houtini/better-search-console"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your-service-account.json"
      }
    }
  }
}

Replace /path/to/your-service-account.json with the actual path to the JSON key file you downloaded in Step 1.

Claude Code (CLI)

Claude Code uses a different registration mechanism -- it doesn't read claude_desktop_config.json. Use claude mcp add instead:

claude mcp add \
  -e GOOGLE_APPLICATION_CREDENTIALS=/p