mcp -gsc
A Model Context Protocol (MCP) server providing access to Google Search Console
claude mcp add --transport stdio ahonn-mcp-server-gsc npx -y mcp-server-gsc \ --env GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
How to use
This MCP server provides programmatic access to Google Search Console data through a configurable API, enabling advanced analytics and filtering capabilities to surface insights about your sites. It exposes a set of tools under the gsc MCP namespace, including a comprehensive search_analytics tool that returns performance metrics with support for dimensions like query, page, country, device, and search appearance. The server is designed to handle large result sets (up to 25,000 rows) and supports complex filtering using regex and multiple operators, making it suitable for in-depth SEO analysis and performance monitoring. Quick Wins detection can be enabled to automatically identify optimization opportunities based on performance signals.
To use the tools, provide the required parameters such as siteUrl, startDate, endDate, and desired dimensions. Optional parameters allow you to refine results with filters, row limits, aggregation types, and data states. Authentication is performed via Google Cloud service account credentials, which must be provided to the server via the GOOGLE_APPLICATION_CREDENTIALS environment variable pointing to a JSON key file. When running, the MCP server will expose endpoints to query search analytics data and apply quick wins logic if enabled.
How to install
Prerequisites:
- Node.js 18 or later
- Access to Google Cloud Project with Search Console API enabled
- Service Account key file (JSON) with appropriate permissions
Installation steps:
- Ensure Node.js is installed. Verify with: node -v
- Install the MCP server package for Google Search Console: npm install mcp-server-gsc
- Prepare Google credentials:
- Create a service account in Google Cloud Console
- Generate a JSON key file and save it securely
- Note the path to the downloaded credentials file
- Run the MCP server using the provided command configuration (adjust paths as needed): npx -y mcp-server-gsc Ensure the environment variable is set to your credentials file, e.g.: GOOGLE_APPLICATION_CREDENTIALS=/path/to/credentials.json
- Verify the server is reachable and the gsc namespace tools are available via your MCP client.
Additional notes
Tips and common considerations:
- Ensure the Google Cloud service account has access to the relevant Search Console properties.
- The credentials file path must be accessible by the server process at runtime.
- For large row results (up to 25,000), consider increasing rowLimit carefully to avoid excessive response times.
- Regex filters for page and query fields require the prefix regex: when using filtering, you can pass patterns like regex:(pattern).
- Quick Wins configuration allows tuning for position ranges, minimum impressions, and CTR thresholds to tailor optimization suggestions to your site.
- If you encounter authentication errors, double-check the project, property access, and that the service account email is granted access in Search Console.
- This server is provided as an npm package (mcp-server-gsc) and is intended to be integrated into an MCP-enabled workflow or client.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud