google-search-console
Model Context Protocol server for Google Search Console API - integrate with Claude Code and Claude Desktop
claude mcp add --transport stdio shin-sibainu-google-search-console-mcp-server npx -y -p google-search-console-mcp-server google-search-console-mcp \ --env GOOGLE_CLIENT_ID="your-client-id.apps.googleusercontent.com" \ --env GOOGLE_CLIENT_SECRET="your-client-secret" \ --env GOOGLE_REFRESH_TOKEN="your-refresh-token"
How to use
This MCP server provides programmatic access to Google Search Console data through Claude Code and Cursor. It exposes a set of tools that let you list your Search Console properties, fetch and analyze performance data, inspect URLs, manage indexing requests, and compare metrics across time periods. The available tools are: list_sites to retrieve all properties you have access to; get_analytics to query search performance with configurable date ranges, dimensions, and row limits; get_sitemaps to fetch sitemap status for a site; inspect_url to check indexing status for a URL; submit_url_for_indexing to request indexing or removal via the Indexing API; and compare_periods to contrast performance between two time windows. Use these tools from Claude Desktop or Claude Code by referencing them by name in natural language prompts, such as “Show me my Google Search Console sites” or “Get search performance data for example.com for the last 7 days.”
How to install
Prerequisites:
- Node.js and npm installed on your machine (required to run npx commands).
- Access to Google Cloud credentials: OAuth 2.0 Client ID/Secret and a refreshed token for the Google Search Console API (and optionally the Indexing API).
- Basic familiarity with Claude Code or Claude Desktop to run MCP commands.
Steps:
- Install Node.js from https://nodejs.org/ if you don’t have it.
- In your project root, create a file named .mcp.json with the configuration provided by the setup steps (see the Quick Start section below).
- Ensure the Google OAuth credentials are prepared:
- CLIENT_ID and CLIENT_SECRET from Google Cloud Console
- A Google OAuth refresh token obtained via the interactive setup command shown below
- Run the MCP server setup via npx to generate the necessary configuration:
npx -y -p google-search-console-mcp-server google-search-console-mcp-setup
This will prompt for GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_REDIRECT_URI, and output a .mcp.json configuration with the GOOGLE_REFRESH_TOKEN. 5) Place the resulting .mcp.json in your project root and reload Claude Code to connect to the MCP server. 6) Start using the tools in Claude Code or Claude Desktop as described in the Usage section.
Additional notes
Tips and common considerations:
- The default Google redirect URI is http://localhost:8080. You can customize this during the OAuth setup if needed.
- If OAuth consent is in Testing mode, add test users to avoid access_denied errors.
- The Indexing API is optional and requires enabling the API in Google Cloud Console along with the indexing scope. Enable it if you plan to use submit_url_for_indexing.
- The mcp.json configuration shown uses npx to fetch and run the package google-search-console-mcp-server. Ensure your environment has network access to npm registries.
- Keep your OAuth credentials secure. Do not commit them to source control.
- The tools validate inputs before API calls to reduce errors and provide actionable guidance when something goes wrong.
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