Google Search Console MCP Server
Provides tools for querying Google Search Console data, including retrieving top search queries by clicks, page performance metrics, overall site search performance summaries, and identifying pages with significant ranking changes.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google Search Console MCP Servershow me top search queries for my site this month"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google Search Console MCP Server
Query Google Search Console data from any AI assistant that supports the MCP protocol - rankings, clicks, impressions, and page-level performance.
Prerequisites
Node.js 18+
A Google account with access to Google Search Console
Setup
1. Install dependencies
npm install2. Create a Google Cloud project
Go to Google Cloud Console
Create a new project (or select an existing one)
Enable the Search Console API:
Go to APIs & Services > Library
Search for "Search Console API"
Click Enable
3. Create OAuth2 credentials
Go to APIs & Services > Credentials
Click Create Credentials > OAuth client ID
Application type: Desktop app (or Web application)
Name it whatever you like
Copy the Client ID and Client Secret
4. Configure your .env file
cp .env.example .envFill in the values:
Variable | Where to find it |
| GSC Settings > Association > Sc-domain (e.g. |
| Google Cloud Console > Credentials (from step 3) |
| Google Cloud Console > Credentials (from step 3) |
5. Run the server
npm startOn first run, a browser window will open automatically to complete OAuth authentication. After that, tokens are stored locally in .tokens.json and you will not be prompted again.
Connecting to your AI assistant
This server communicates over stdio (standard input/output), which is the standard way to connect MCP servers to AI assistants. Configure your AI assistant to use:
node /path/to/src/index.jsReplace /path/to with the actual path to this project on your machine.
Available tools
getTopQueries
Returns your top search queries ranked by clicks.
Parameters:
startDate(YYYY-MM-DD),endDate(YYYY-MM-DD),rowLimit(optional, default 10)Returns: query, clicks, impressions, CTR, position for each row
getSiteSummary
Returns overall site search performance totals.
Parameters:
startDate(YYYY-MM-DD),endDate(YYYY-MM-DD)Returns: total clicks, impressions, CTR, average position
getPagePerformance
Returns performance data filtered to a specific page.
Parameters:
pageUrl(exact URL as shown in GSC),startDate(YYYY-MM-DD),endDate(YYYY-MM-DD)Returns: clicks, impressions, CTR, position for that page
getRankingChanges
Finds pages with the biggest position changes between two periods.
Parameters:
days(number of days to compare, default 28)Returns: page URL, position change, current position, prior position
Important
Never commit .env or .tokens.json to version control. These files are already excluded via .gitignore.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Appeared in Searches
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bwengr/bw-gsc-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server