Server health: credentials, local database, inspection queues, background jobs, robots.txt watches, today's inspection quota use.

All Search Console properties this Google account can access, with permission level.

One-call overview: web + Discover performance vs previous period, sitemaps health, local indexing summary, robots.txt status.

Search performance (clicks, impressions, CTR, position) for any dimension combination, search type, date range and filters.

Totals vs the previous equal-length period, daily series, top queries and pages. Use search_type='discover' for Discover.

Winners and losers between two periods (default: previous equal-length period), with new and lost queries/pages.

Quick wins: striking-distance query/page pairs, top positions with low CTR (vs this site's own CTR by position), and content gaps (demand, but ranking below 20).

Queries where 2+ of your URLs split impressions. URL variants (www/non-www, http/https, slash, parameters) are reported separately from genuinely competing pages.

Pages/queries that lost clicks vs the previous period, each diagnosed: ranking loss, CTR drop, demand drop or disappeared, with the click loss split exactly into fewer impressions vs lower CTR.

Pages (or queries) whose clicks fell in every one of N consecutive periods: slow decay, not a one-off dip.

Severity-rated alerts: site-wide click drop, query position drops (incl. falling off page one), CTR collapses at the same position, page click losses, pages that vanished.

Performance per site section (URL folder or custom prefixes) with share of clicks and change vs the previous period. Domain properties are split per host.

Queries split into branded vs non-branded, questions (EN/NL/SV/PT/FR/DE), query length, results page, and chat-style fragments.

Health check across many properties at once: clicks, impressions, CTR, position vs previous period, flagged dropping/growing.

Full report in one call (performance, alerts, drops, quick wins, content gaps, decay, cannibalisation, sitemaps, indexing, robots.txt), saved as a Markdown file.

Re-query Google to confirm a number before presenting it (e.g. 'this page got 500 clicks').

Sitemaps submitted for the property: last submitted/downloaded, pending, errors, warnings, submitted URL counts by type.

Details of one submitted sitemap.

Live URL Inspection result from Google (index status, coverage reason, canonicals, last crawl, robots, sitemaps, referring URLs, rich results). Stored locally.

Why is this URL (not) indexed? Combines Google's inspection with a live fetch: redirect chain, status, noindex, canonicals, robots.txt rule, thin content.

Add URLs to this property's local inspection queue.

Download sitemaps (indexes, .gz) and queue every page URL for inspection, remembering which sitemap each URL came from.

Queue every page that got impressions in Search (useful to inspect the pages Google actually shows).

Inspect URLs now: the queue (never-inspected first, then stale), an explicit list, or your top pages. Respects the 2,000/day and 600/minute per-property quotas.

Background inspection while Claude Desktop is open: works through the queue within the daily quota and resumes after restarts.

Page-indexing report from local inspections: indexed vs not, every reason with source, samples, checks and fixes; canonicals, fetch/robots states, crawl age, rich results.

URL-level drill-down of stored inspections with filtering, sorting, paging and CSV export.

URLs whose coverage reason changed between their last two inspections (dropped out of the index, newly indexed, ...), plus per-day inspection trend.

What each Page indexing reason means, whether it's a Website or Google-systems issue, what to check and how to fix it.

Fetch robots.txt like Googlebot: status and Google's interpretation, size vs the 500 KiB limit, groups, Googlebot rules, sitemaps, syntax warnings, and a diff if it changed since the last check. Saved to history.

Check robots.txt on every host that had Search traffic in the property (all subdomains of a Domain property).

Every stored robots.txt check for a host (date, status, size, hash, response time) and each distinct version with first/last seen.

Unified diff between two stored robots.txt checks (ids from robots_txt_history).

Is this URL allowed for this crawler? Returns the deciding rule and line, using Google's matching rules.

Keep checking robots.txt for a host in the background (while Claude Desktop is open) to build version history.

Trace redirect chains in bulk: every hop, final status, chains, loops, temporary redirects, https->http; validates migration redirect maps.

HTTPS health (Search Console's HTTPS report has no API): certificate validity/expiry/names, http->https redirect, HSTS, mixed content.

DNS records (A, AAAA, CNAME, MX, NS, TXT, CAA) plus Google site-verification tokens found in DNS TXT and on the home page.

Image SEO audit of pages: alt text, file names, width/height, lazy loading near the top, formats, file size, broken images, og:image and structured-data images.

PageSpeed Insights: Lighthouse scores, lab metrics, top opportunities by savings, failing SEO/other audits, and real-user field data. Uses PAGESPEED_API_KEY or CRUX_API_KEY if set.

Context saved with a property for future chats: brand terms, migration dates, decisions, site changes.

Import Apache/Nginx/Varnish access logs to rebuild Crawl stats. Runs in the background; already-imported files are skipped.

Crawl stats from your logs: requests, download size, response time per day; breakdowns by response, file type, Googlebot type, purpose and host; robots.txt fetches; example URLs.

Core Web Vitals field data (LCP, INP, CLS, FCP, TTFB at p75) from the Chrome UX Report, the data behind Search Console's CWV report. Needs CRUX_API_KEY.