About Google Search Console MCP Server
Google Search Console MCP Server is an MCP server that gives AI agents access to Search Console search performance data, keyword rankings, sitemaps and indexing status. It is intended for SEO analysis from MCP clients such as Claude, Cursor and Windsurf.
Key features
- 01Query clicks, impressions, CTR and average position
- 02List verified sites with permission levels
- 03Inspect URL index status and crawl issues
- 04List, submit and delete XML sitemaps
- 05Install quickly with uvx or npx
Use cases
- 01Asking an AI agent to analyse keyword rankings and search performance
- 02Troubleshooting indexing and crawl problems on specific pages
- 03Managing sitemap submission and cleanup
MCP support
The project is an MCP server that exposes tools such as get_search_analytics, inspect_url and list_sitemaps, plus skill_read and skills_list, to MCP clients including Claude, Cursor and Claude Code.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx google-search-console-mcpGOOGLE_APPLICATION_CREDENTIALSSecretAbsolute path to your Google Cloud service account JSON key fileLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Search Console (GSC) MCP Server 🔍
Model Context Protocol (MCP) server for Google Search Console: search performance analytics, keyword rankings, sitemap inspection, and indexing health for AI agents.
🌐 Live Documentation & Web Portal: https://gsc.builditwithai.xyz
⚡ Quickstart
# 1-Line Universal Installer (Auto-configures Claude Desktop, Cursor, Claude Code, Antigravity, VS Code, Zed, Windsurf)
curl -fsSL "https://gsc.builditwithai.xyz/install" | bash
# Or run directly via your preferred runtime:
uvx google-search-console-mcp
npx -y @surendranb/google-search-console-mcp
🤖 Client Setup
A. Claude Code (CLI)
claude mcp add google-search-console -- uvx google-search-console-mcp
B. Cursor & Google Antigravity (mcp.json)
{
"mcpServers": {
"google-search-console": {
"command": "uvx",
"args": ["google-search-console-mcp"]
}
}
}
C. Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"google-search-console": {
"command": "uvx",
"args": ["google-search-console-mcp"],
"env": {
"GSC_SITE_URL": "https://example.com/",
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service_account.json"
}
}
}
}
D. VS Code (Cline / Roo Code / Continue)
{
"mcpServers": {
"google-search-console": {
"command": "npx",
"args": ["-y", "@surendranb/google-search-console-mcp"]
}
}
}
🛠️ Tools & Capabilities
| Tool Name | Parameters | Description | Return Type |
|---|---|---|---|
get_search_analytics | site_url (string), start_date (string), end_date (string), dimensions (list), row_limit (int) | Queries organic search clicks, impressions, CTR, and average position grouped by query, page, country, device, and date. | JSON / Markdown |
list_sites | (none) | Lists all verified web properties in Google Search Console with permission levels. | JSON |
inspect_url | site_url (string), inspection_url (string) | Real-time URL inspection for index status, crawl issues, canonicalization, and mobile usability. | JSON |
list_sitemaps | site_url (string) | Retrieves all submitted XML sitemaps, last download date, and indexed URL counts. | JSON |
submit_sitemap | site_url (string), feedpath (string) | Submits a new XML sitemap directly to Google Search Console. | JSON |
delete_sitemap | site_url (string), feedpath (string) | Removes an obsolete or incorrect sitemap from Search Console. | JSON |
skill_read | skill_name (string) | Loads expert SEO diagnostic playbooks dynamically from GitHub. | Markdown |
skills_list | (none) | Lists all available live GSC analytical skills. | JSON |
🔒 Telemetry & Privacy
This package collects anonymous, non-PII diagnostic telemetry (command executions, latency, error codes) to improve tool reliability. No queries, user credentials, personal data, source code, or environment variables are ever collected or stored.
You can opt out anytime by setting either of the following environment variables:
export DO_NOT_TRACK=1
# or
export MCP_TELEMETRY_OPT_OUT=1
📄 License
MIT License. See LICENSE for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.