MCP Server · Remote · Organic search data

Google Search Console MCP Server

NotFair's Google Search Console MCP exposes your organic-search data as a typed tool surface for AI agents. Built on the Model Context Protocol. Connect Claude, Codex, or any compliant client at https://notfair.co/api/mcp/google_search_console and ask questions over live Google Search Console data — top queries, page CTR, index coverage, and sitemaps.

OAuth 2.0 with PKCE · No Client ID or Secret · Read tools plus approval-gated sitemap writes.

Tool surface

What Claude can do with Google Search Console

Read tools scoped to the properties you connect, plus approval-gated sitemap management. Every write is proposed in chat and confirmed before it reaches Google.

Tool
listProperties
getSearchAnalytics
inspectUrl
listSitemaps
submitSitemap
deleteSitemap
runScript

Connector name in Claude / Codex configs: NotFair-GoogleSearchConsole

Connect Google Search Console and try it in Claude

Authorize NotFair to read your Google Search Console, then add the MCP server to Claude. The first prompt to try: “Which pages have high impressions but low CTR over the last 28 days?”

FAQ — Google Search Console MCP Server

Everything you need to know about the NotFair Google Search Console MCP server, its auth model, and the tool surface.

What is the NotFair Google Search Console MCP server?

It's a remote MCP (Model Context Protocol) server at https://notfair.co/api/mcp/google_search_console that exposes your Google Search Console properties as a typed tool surface for AI agents. Claude Desktop, Claude.ai Web, Claude Cowork, Claude Code, and Codex can all connect to it and answer questions over live organic-search data — top queries, page CTR, index coverage, and sitemaps.

How does authentication work?

Claude.ai's Add custom connector flow and Codex both use OAuth 2.0 with PKCE — there's no Client ID or Secret to copy. You authorize NotFair to read your Google Search Console once, pick which verified properties to expose, and the connection is scoped to those properties and revocable at any time.

What Google Search Console data is exposed?

Verified properties and their permission levels, Search Analytics (clicks, impressions, CTR, average position) grouped by query, page, country, device, or date, single-URL index inspection (coverage, canonical, crawl, mobile usability, rich results), and submitted sitemaps with their warning and error counts. Tokens are encrypted at rest and refreshed server-side.

Can the AI change anything, or is it read-only?

Reads are unrestricted. The only writes are sitemap management — submitSitemap and deleteSitemap — and both are approval-gated: the change is proposed in chat, you confirm, and each is reversible. There are no destructive tools beyond sitemap removal, which submitSitemap reverses.

How fresh is the Search Analytics data?

By default getSearchAnalytics returns finalized data, which lags roughly 2-3 days behind real time. You can request the 'all' data state to include the most recent, still-changing rows. Note that query-dimension rows omit anonymized low-volume queries, so they will not sum exactly to property totals — that's a Google Search Console API behavior, not a NotFair one.

Does it handle both domain and URL-prefix properties?

Yes. listProperties returns both forms — domain properties look like sc-domain:example.com and URL-prefix properties look like https://example.com/. Every property-scoped tool accepts whichever identifier the property uses.

How do I disconnect?

From /connect/google_search_console you can revoke access at any time. That removes the stored credential and invalidates the Claude and Codex OAuth tokens issued for the connection.