MCP Hub
Back to servers

searchconsole-mcp

Provides read-only access to Google Search Console data, allowing AI assistants to query site performance metrics like keywords, clicks, and rankings using natural language. It supports listing verified properties, querying search analytics with dimension filters, and retrieving sitemap information.

Updated
Feb 1, 2026

searchconsole-mcp

CI Python 3.11+ License: MIT

An MCP server that gives AI assistants read-only access to your Google Search Console data. Ask questions about your site's search performance in natural language — keywords, clicks, impressions, CTR, rankings, sitemaps, and more.

Tools

ToolDescription
list_sitesLists all verified Search Console properties with permission levels
query_search_analyticsQuery keyword/page data — clicks, impressions, CTR, average position. Supports filtering by dimension, date range, search type, and pagination
list_sitemapsLists submitted sitemaps for a property

Quick Start

1. Install

git clone https://github.com/chrishart0/searchconsole-mcp.git
cd searchconsole-mcp
uv sync

2. Authenticate

This server uses Google Application Default Credentials. Choose one:

Option A — Service account key (recommended for automation):

export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json

Option B — User credentials (recommended for local development):

gcloud auth application-default login \
  --scopes="https://www.googleapis.com/auth/webmasters.readonly"

The service account or user must have access to the Search Console properties you want to query.

3. Connect to your MCP client

Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "searchconsole-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/searchconsole-mcp", "searchconsole-mcp"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/key.json"
      }
    }
  }
}
Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "searchconsole-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/searchconsole-mcp", "searchconsole-mcp"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/key.json"
      }
    }
  }
}
Other MCP clients

Any MCP-compatible client can connect over stdio. Run the server with:

uv run --directory /path/to/searchconsole-mcp searchconsole-mcp

Example Prompts

Once connected, try asking your AI assistant:

  • "What are my top 10 keywords by clicks this month?"
  • "Show me pages with high impressions but low CTR"
  • "List all my Search Console properties"
  • "What queries is my site ranking for on page 2 of Google?"
  • "Show me my sitemaps and their status"

Development

uv sync --dev
uv run pytest

License

MIT

Reviews

No reviews yet

Sign in to write a review