This is a community-maintained, MIT-licensed, unofficial MCP server that connects Google Search Console to MCP-capable AI clients. Its strengths are broad coverage of the SEO workflow — properties, search analytics, URL inspection, and sitemap management — plus uvx-based installation without cloning, two authentication options, and optional sse transport for remote deployment. The trade-off is that users must create their own Google Cloud credentials and manage credentials and account permissions themselves, and the cloned install requires Python 3.11+. It suits SEO users willing to set things up themselves, and is not aimed at those who only want a web interface or don't want to manage credentials.
This is a Model Context Protocol (MCP) server that connects Google Search Console (GSC) to AI assistants so you can analyze SEO data through natural-language conversation. It covers property management, search analytics and reporting, URL inspection and indexing status, and sitemap management, and can have the assistant visualize data with charts. The server runs locally and supports two authentication paths: OAuth browser sign-in (recommended, uses your own Google account) or a service account (for automation or team use). Client configs require absolute paths to your credentials file; on first use OAuth opens a browser window, after which the token is cached. It can run without installation via uvx, or from a cloned repository (requires Python 3.11+). It also supports remote/network deployment with MCP_TRANSPORT=sse and running in Docker. Tools provided include property listing, site details, search analytics, performance overview, period comparison, per-page queries, advanced filtered analytics, URL inspection, batch URL inspection, indexing issue checks, sitemap viewing and management, reauthentication, and get_capabilities.
{
"mcpServers": {
"gscServer": {
"command": "/FULL/PATH/TO/uvx",
"args": ["mcp-search-console"],
"env": {
"GSC_OAUTH_CLIENT_SECRETS_FILE": "/full/path/to/client_secrets.json"
}
}
}
}