List the Google accounts this server can act as, and which one is used when a tool call does not name one. Pass an email as the account argument on any other tool to switch.

Every Search Console property this Google account can reach, with the permission level on each: siteOwner, siteFullUser, siteRestrictedUser or siteUnverifiedUser. Start here. The siteUrl strings it returns are the exact values every other tool wants, and copying one avoids the trailing-slash and sc-domain: mismatch that surfaces as a permissions error.

One property and the permission level this account holds on it.

Register a property in Search Console. This only adds it: the property stays unverified and returns no data until ownership is proven, so follow with get_verification_token and verify_site. Adding a property that is already there is a no-op rather than an error.

Remove a property from this Google account's Search Console. The site's history is no longer readable by this account until the property is re-added and re-verified, and Google does not offer an undo. Set confirm to true to proceed.

The core report: clicks, impressions, CTR and average position from Google Search, grouped by any combination of query, page, country, device, searchAppearance, date or hour. This is the full-control tool. For the questions people actually ask, top_queries, top_pages, striking_distance and compare_periods are one call instead of a hand-assembled body. Two things to know before reading a result as bad news. Data finalises on a two to three day lag, so a window ending today is short at the end. And Google withholds rare queries for privacy, which is why the query breakdown reliably sums to fewer clicks than the site total.

The search queries bringing the most clicks to a property, with impressions, CTR and average position. Defaults to the last 28 days ending three days ago, because Search Console lags and a window ending today reads as empty.

The pages on a property earning the most clicks from Google Search, with impressions, CTR and average position. Defaults to the last 28 days ending three days ago.

Two equal windows side by side with the deltas already computed: what went up, what fell, per query, page, country or device. This is the tool for "what changed", "are we up or down" and "which pages lost traffic". The default compares the last 28 days against the 28 before them. Rows are sorted by click change, so the biggest losses are at the bottom and the biggest gains at the top.

Queries a property already ranks for on the edge of page one, between positions 5 and 20 by default, ordered by the impressions being left on the table. These are the pages where a title rewrite or a section of added depth moves traffic, because the ranking work is already done. The single most useful report in Search Console and the UI makes you build it by hand every time.

Every sitemap submitted for a property, with when Google last downloaded each one, how many URLs it holds per content type, and any warnings or errors. A sitemap Google has quietly stopped reading shows up here as a lastDownloaded date that stopped moving, which nothing in the UI puts in front of you.

Details for one submitted sitemap: last download, last submitted, URL counts per type, and whether it is pending or errored.

Submit or resubmit a sitemap. This is the only way the API can ask Google to recrawl anything: there is no endpoint behind the "Request indexing" button, so resubmitting after publishing is the programmatic equivalent. Returns immediately. Google fetches the file on its own schedule, so read the result back with get_sitemap rather than expecting counts here.

Stop tracking a sitemap on a property. It does not deindex the URLs the sitemap listed, and it does not delete the file. What it does lose is the submission history and per-sitemap coverage for it. Set confirm to true to proceed.

Ask Google what it actually knows about one URL: whether it is indexed, which sitemap it was found in, the canonical Google picked against the one the page declares, the last crawl, mobile usability, rich results and any AMP version. This is the tool for "why is this page not showing up". Two constraints worth knowing before a loop: the URL has to sit under the property, and the quota is roughly 2000 inspections a day and 600 a minute per property, so inspect the pages that matter rather than a whole site.

Inspect several URLs on the same property in one call and get a compact table back: indexed or not, the canonical Google chose, and the last crawl. Use it to check a batch of pages after a launch or a migration. Requests run a few at a time to stay inside the per-minute quota, and one URL failing does not sink the rest. Keep batches small: the daily quota is about 2000 inspections per property.

Mint the token that proves ownership of a site or domain, so a new property can be verified without opening the Search Console UI. A domain property must use DNS: publish the returned token as a TXT record on the apex. A URL-prefix property can instead use META, a tag in the homepage head, or FILE, a file served at the site root. Publish the token first, then call verify_site. Minting a token changes nothing on its own.

Claim ownership once the token from get_verification_token is live. Google fetches the DNS record, meta tag or file and, if it matches, marks this Google account an owner of the site. It fails until the token is actually reachable, which with DNS means waiting for propagation, sometimes several minutes. Retrying is safe.

Every site and domain this Google account has verified ownership of, across all Google products. This is a wider list than list_sites, because a verified domain is not automatically a Search Console property. Use it to tell "not verified yet" apart from "verified but never added", which are two different fixes.