Connect Google Search Console to Claude Desktop with an MCP Server — A Complete Guide

Perfect for non-coders, SEOs, marketers, and founders who want to pull real Google Search Console data into Claude Desktop — using a local, secure Python-powered MCP server.

What is an MCP Server?

MCP (Model Context Protocol) servers allow AI tools like Claude to interact with real-world data and tools via a standard protocol. Think of it like a bridge between your local data (like GA4 or Shopify) and Claude’s chat interface — so Claude can ask for data and act on it using well-defined tools, all running securely on your machine.

If you want to know more about How Marketers can use  MCP servers, here’s a detailed guide: The End-to-End Model Context Protocol (MCP) Guide for Marketers

What You’ll Achieve

• Query your Search Console performance in Claude (e.g., “Show my top keywords for the last 28 days”)
• Run everything locally — you stay in control of your data
• Use Claude like a smart SEO assistant plugged into your actual GSC data

Tools You’ll Need 🛠️

Tool	Why You Need It
Claude Desktop	To access and chat with tools
Python (3.10+)	To run the MCP server locally
Git (optional)	To clone the project repository
Google Search Console Access	Google Search Console

 🚀 Need Help With the Setup?

 If the setup feels too technical, our team is here to help.

Don’t worry,  we’ve got your back!

 👉 Click here to get expert assistance now!

Prerequisites

Before starting either of the methods, make sure:

1. You have Python installed

Download it from python.org. During install:

• Check “Add Python to PATH” ( VERY IMPORTANT STEP)
• Then click Install Now

To confirm it’s installed:

Open your command line:

• Windows: Press Win + R, type cmd, and press Enter
• macOS: Press Cmd + Space, type Terminal, and hit Enter
• Linux: Press Ctrl + Alt + T, or open Terminal from your applications menu

Then run this text below:

python --version

If installed correctly, you should see it return something like: Python 3.10.13

( Note: the number next to Python might differ based on the version you have downloaded )

2. You’ve installed Claude Desktop

Claude Desktop is required to use MCP servers.

Download the desktop app from Anthropic’s official Claude site. ( https://claude.ai/download )

Step 1: Clone or Download the GSC MCP Project

Option A: Clone with Git (Recommended)

git clone https://github.com/seotesting-com/gsc-mcp-server.git
cd gsc-mcp-server

Option B: Download ZIP

• Visit: https://github.com/seotesting-com/gsc-mcp-server
• Click Code → Download ZIP
• Extract to a folder (e.g., Documents/mcp-ga4)

Step 2: Create Your Virtual Environment

1. Open your terminal or command prompt
2. Navigate to the project folder:

cd path/to/your/gsc-mcp-server

  3. Create a virtual environment by using this line below:

python -m venv .venv

4. Activate it:

• Windows

.venv\Scripts\activate

• macOS/Linux

source .venv/bin/activate

Step 3: Install Dependencies

Inside the same activated terminal:

pip install -r requirements.txt

You should see a lot of dependencies being downloaded and the sync would have been given.

Step 4: Get Your Google Search Console Credentials

1. Visit Google Cloud Console
2. Create a new project or select an existing one
3. Go to APIs & Services → Library
4. Search for Search Console API, click it, and press Enable
5. Go to APIs & Services → Credentials
6. Click Create Credentials → OAuth client ID
   • Application type: Web application
   • Authorized redirect URI: use http://localhost:8000/oauth2callback
7. Download the client_secrets.json file and save it in the gsc-mcp-server folder.

Step 5: Authorize the App

1. Run the app for the first time to generate the OAuth flow:

 uvicorn main:app --reload

2. Visit http://localhost:8000/authorize in your browser
3. Log in with your Google account
4. Grant access to your Search Console data
5. This will generate a token.json file in your project folder — this stores your credentials locally.

Step 6: Register the MCP Server with Claude Desktop

1. Run this command to install the server:
   
    

run mcp install main.py

2. Open Claude Desktop → Settings → Developer → Edit Config

A folder will open with claude.json.

1. Add this under "mcpServers":

"Google Search Console": {
"command": "uvicorn",
"args": [
"main:app",
"--reload"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "C:\Path\To\Your\gsc-mcp-server\client_secrets.json"
}
}

Note: You make sure the paths match your local folder!

Step 7: Ask Claude!

Restart Claude Desktop completely (check Task Manager to ensure no stray instances).

Open Claude and ask

Get my top 10 keywords from Google Search Console for the last 28 days.

Claude will detect your GSC MCP server and pull real data!

Troubleshooting Tips

• ❌ No tools in Claude? → Double-check your claude.json paths and restart Claude.
• ❌ OAuth failed? → Make sure your redirect URI matches http://localhost:8000/oauth2callback
• ❌ Permission denied? → Confirm your Google account has access to the GSC property.

That’s It!

You now have a fully working, local Google Search Console MCP server talking directly to Claude Desktop.

All your data stays private and you get real SEO insights — no third-party cloud needed.

Check out our other blogs for more information on MCP servers and various other tools that will end up making your life easy:

• The End-to-End Model Context Protocol (MCP) Guide for Marketers
• Top AI Tool Libraries To Find the Best AI Tools
• Notebook LM: A Guide with Use Cases and Examples

FAQs