Google Search Console MCP server for AI agents

This MCP server connects Google Search Console (GSC) with Claude AI, allowing you to analyze SEO data through natural language conversations. You can access property information, search analytics, URL inspection, and sitemap management by simply chatting with Claude.

Installation Requirements

Before getting started, you'll need to install:

Python (version 3.11 or newer)
Node.js
Claude Desktop

Setting Up Google Search Console API Access

The tool supports two authentication methods:

OAuth Authentication (Recommended)

Go to the Google Cloud Console
Create a new project or select an existing one
Enable the Search Console API for your project
Add scope https://www.googleapis.com/auth/webmasters
Go to the "Credentials" page
Click "Create Credentials" and select "OAuth client ID"
Configure the OAuth consent screen
For application type, select "Desktop app"
Give your OAuth client a name and click "Create"
Download the client secrets JSON file

Service Account Authentication

Go to the Google Cloud Console
Create a new project or select an existing one
Enable the Search Console API
Go to the "Credentials" page
Click "Create Credentials" and select "Service Account"
Fill in the service account details and click "Create"
Click on the newly created service account
Go to the "Keys" tab and click "Add Key" > "Create new key"
Select JSON format and click "Create"
Download the key file and save it as service_account_credentials.json
Add your service account email address to appropriate Search Console properties

Installing the MCP Server

Download the tool:
```
git clone https://github.com/AminForou/mcp-gsc.git
```
Or download the ZIP file from the GitHub repository and unzip it.
Navigate to the folder in terminal:
```
cd path/to/mcp-gsc-main
```

Create a virtual environment:

# Using uv (recommended):
pip install uv
uv venv .venv

# OR using standard Python:
python -m venv .venv

Activate the virtual environment:

# On Mac/Linux:
source .venv/bin/activate

# On Windows:
.venv\Scripts\activate

Install dependencies:

# Using uv:
uv pip install -r requirements.txt

# OR using standard pip:
pip install -r requirements.txt

Connecting Claude to Google Search Console

Open your Claude Desktop configuration file:

# For Mac users:
nano ~/Library/Application\ Support/Claude/claude_desktop_config.json

# For Windows users:
notepad %APPDATA%\Claude\claude_desktop_config.json

Add the appropriate configuration:

For OAuth authentication:

{
  "mcpServers": {
    "gscServer": {
      "command": "/FULL/PATH/TO/.venv/bin/python",
      "args": ["/FULL/PATH/TO/mcp-gsc-main/gsc_server.py"],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "/FULL/PATH/TO/client_secrets.json"
      }
    }
  }
}

For service account authentication:

{
  "mcpServers": {
    "gscServer": {
      "command": "/FULL/PATH/TO/.venv/bin/python",
      "args": ["/FULL/PATH/TO/mcp-gsc-main/gsc_server.py"],
      "env": {
        "GSC_CREDENTIALS_PATH": "/FULL/PATH/TO/service_account_credentials.json",
        "GSC_SKIP_OAUTH": "true"
      }
    }
  }
}

Replace all paths with the actual locations on your computer.

Save the file and restart Claude Desktop

Using the GSC Tools with Claude

Once connected, you can use the following tools by asking Claude:

Property Management

list_properties - Shows all your GSC properties
get_site_details - Shows details about a specific site
add_site - Adds a new site to your GSC properties
delete_site - Removes a site from your GSC properties

Search Analytics

get_search_analytics - Shows top queries and pages with metrics
get_performance_overview - Gives a summary of site performance
get_search_by_page_query - Analyzes search terms driving traffic to specific pages
compare_search_periods - Compares performance between different time periods
get_advanced_search_analytics - Provides detailed analytics with filtering options

URL Inspection

check_indexing_issues - Checks if pages have indexing problems
inspect_url_enhanced - Detailed inspection of a specific URL
batch_url_inspection - Inspects multiple URLs at once

Sitemap Management

get_sitemaps - Lists all sitemaps for your site
list_sitemaps_enhanced - Provides enhanced sitemap information
submit_sitemap - Submits a new sitemap to Google
get_sitemap_details - Checks the status of a specific sitemap

Example Prompts

Here are some effective prompts you can use:

"List all my GSC properties and tell me which ones have the most pages indexed."
"Show me the top 20 search queries for mywebsite.com in the last 30 days, highlight any with CTR below 2%."
"Check these important pages for indexing issues: mywebsite.com/product, mywebsite.com/services"
"Compare my site's performance between January and February. What queries improved the most?"
"Analyze my mobile search performance for queries with high impressions but positions below 10."

Troubleshooting

Python Command Not Found

On macOS, create a Python alias:

sudo ln -s $(which python3) /usr/local/bin/python

Configuration Issues

Ensure all file paths in your configuration are correct and use full paths
Check that your service account has access to your GSC properties
Restart Claude Desktop after making configuration changes
Look for error messages in Claude's response

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "gscServer" '{"command":"/FULL/PATH/TO/-main/.venv/bin/python","args":["/FULL/PATH/TO/mcp-gsc-main/gsc_server.py"],"env":{"GSC_OAUTH_CLIENT_SECRETS_FILE":"/FULL/PATH/TO/client_secrets.json"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "gscServer": {
            "command": "/FULL/PATH/TO/-main/.venv/bin/python",
            "args": [
                "/FULL/PATH/TO/mcp-gsc-main/gsc_server.py"
            ],
            "env": {
                "GSC_OAUTH_CLIENT_SECRETS_FILE": "/FULL/PATH/TO/client_secrets.json"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "gscServer": {
            "command": "/FULL/PATH/TO/-main/.venv/bin/python",
            "args": [
                "/FULL/PATH/TO/mcp-gsc-main/gsc_server.py"
            ],
            "env": {
                "GSC_OAUTH_CLIENT_SECRETS_FILE": "/FULL/PATH/TO/client_secrets.json"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect