The mcp-gsc server allows users to query Google Search Console data, inspect URLs, manage sitemaps, and perform analytics using natural language. It is built with Bun and TypeScript and is compatible with various MCP clients.
From the registry: Google Search Console MCP server — query performance, sitemaps, indexing & more
$ npx mcp-gsc setupPlease install the `mcp-gsc` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Google Cloud OAuth credentials** — Create an OAuth client (Desktop app) in Google Cloud Console, enable the Google Search Console API, and download the JSON credentials file (https://console.cloud.google.com/apis/credentials)
- **Authorize via setup** — Run setup to complete OAuth and cache refresh token Run: `npx mcp-gsc setup`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","mcp-gsc@latest"]
- required environment variables:
- `GOOGLE_GSC_CREDENTIALS_PATH`: Path to OAuth client JSON or service account key (example: `/path/to/credentials.json`)
- optional environment variables:
- `GOOGLE_GSC_PROPERTY`: Default GSC property URL (e.g. sc-domain:example.com) (example: `<your-property>`)
- `GOOGLE_GSC_ENABLE_WRITES`: Enable write tools (add_site, delete_site, submit_sitemap, delete_sitemap) (example: `false`)
- `GOOGLE_GSC_ENABLE_EXTENDED_TOOLS`: Enable extended analytics tools (13 extra) (example: `false`)
Note: Google Search Console MCP server (25 tools). Requires Node 18+. Service account auth supported as alternative.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_GSC_CREDENTIALS_PATHrequiredPath to OAuth client JSON or service account keyMCP server for searching Airweave collections with natural language queries.