# @surendranb/google-search-console-mcp [Health: Active]

**Category:** 🎯 Marketing  
**Repository:** https://github.com/surendranb/google-search-console-mcp  
**GitHub Stars:** 40  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/surendranb-google-search-console-mcp

## Description
Model Context Protocol (MCP) server for Google Search Console (GSC) inspection, search performance, and sitemaps via NPX. Spawns the Python package through uvx with full stdio passthrough.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "google-search-console-mcp": {
    "command": "uvx",
    "args": ["google-search-console-mcp"],
    "env": {
      "GSC_SITE_URL": "",
      "GOOGLE_APPLICATION_CREDENTIALS": ""
    }
  }
}
```

**Requires environment variables:** `GSC_SITE_URL`, `GOOGLE_APPLICATION_CREDENTIALS` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What @surendranb/google-search-console-mcp does

The @surendranb/google-search-console-mcp MCP server exposes Google Search Console operations to MCP-compatible AI clients. It covers both reporting and administrative workflows: an agent can query organic search metrics, find verified properties, inspect a URL’s indexing state, review submitted sitemaps, and submit or remove sitemap entries.

Search analytics results can be grouped by query, page, country, device, or date. The analytics tool accepts a site, date range, dimensions, and row limit, and returns JSON or Markdown. URL inspection reports index status, crawl problems, canonicalization, and mobile-usability information.

The package also includes a live skills interface. Agents can list available GSC analytical skills and load an individual SEO diagnostic playbook from GitHub when additional guidance is needed.

## How it works

The server communicates over standard input and output. The npm package acts as a launcher for the Python package, so it can be started with `npx -y @surendranb/google-search-console-mcp`; the underlying package can also be started with `uvx google-search-console-mcp`.

A client starts the process and supplies the Google service-account credential path and site configuration through its environment. Once authenticated, the available tools call Google Search Console for the requested property. Some operations, including site listing, do not require tool parameters, while others require a site URL and operation-specific values such as dates, an inspection URL, or a sitemap path.

## Setup and configuration

The @surendranb/google-search-console-mcp MCP server can be added to clients using either the `uvx` command or the npm launcher. The repository documents configurations for Claude Desktop, Cursor, Claude Code, VS Code-based clients, Zed, Windsurf, Cline, Roo Code, and Continue. A provided installer can also configure several supported clients automatically.

Set `GOOGLE_APPLICATION_CREDENTIALS` to the path of a Google service-account JSON file. The documented Claude Desktop example also sets `GSC_SITE_URL` to the Search Console property URL. The client must be able to access the credentials file, and the service account must have suitable access to the relevant Search Console properties.

Anonymous diagnostic telemetry covers command executions, latency, and error codes. The documentation states that queries, credentials, personal data, source code, and environment variables are not collected or stored. Set `DO_NOT_TRACK=1` or `MCP_TELEMETRY_OPT_OUT=1` to opt out.

## Tools and capabilities

- `get_search_analytics` retrieves clicks, impressions, click-through rate, and average position for a selected date range and grouping.
- `list_sites` returns verified Search Console properties and permission levels.
- `inspect_url` checks index status, crawl issues, canonicalization, and mobile usability for a URL.
- `list_sitemaps` reports submitted XML sitemaps, download dates, and indexed URL counts.
- `submit_sitemap` submits an XML sitemap to a selected property.
- `delete_sitemap` removes a sitemap from Search Console.
- `skills_list` lists available live GSC analytical skills.
- `skill_read` loads a named SEO diagnostic playbook from GitHub.

These capabilities make the server suitable for investigating ranking and indexing data, checking individual pages, and maintaining sitemap submissions through an AI client.

_Full upstream README: https://allmcps.com/mcp/surendranb-google-search-console-mcp/readme_