Start a Hubertino scrape that searches Google Maps for businesses and returns them as lead rows (name, category, phone, website, email, address, rating, reviews, social profiles). Use it for requests like "find dentists in Austin with emails" or "build a list of plumbers in Leeds". Every category is searched in every location: categories x locations searches, max 2000 per scrape. COSTS CREDITS: it reserves categories x locations x maxResults credits up front (capped at the balance), charges 1 credit per business actually delivered and refunds the rest. Confirm with the user before large scrapes. Returns the scrape id immediately (status queued); then call wait_for_scrape, then get_results or download_export. Limited to 12 new scrapes per 5 minutes per account.

Get one scrape's live status (queued, running, done, error), progress (stage, percent, searches done, places found/extracted), resultCount, credits reserved/charged, and coverage (how many delivered rows have an email, phone, website, socials...). Use it to check on a scrape without waiting; use wait_for_scrape to block until it finishes.

Poll a scrape until it is done (or failed), or until timeoutSeconds passes, then return its status like get_scrape. If it is still running when the time is up, just call wait_for_scrape again. Sends MCP progress notifications when the client asks for them. Many MCP clients abort a tool call after about 60 seconds, so keep the default timeout unless you know yours allows more.

List this account's most recent scrapes, newest first (the API keeps the latest 200): id, title, status, resultCount, credits charged and dates. Use it to find a scrape id or to reuse a finished scrape instead of paying for the same search again.

Read a scrape's rows as compact JSON, one page at a time. Works while the scrape is running (partial rows) and after it is done. Long pages are cut short to fit one tool response (trimmed: true); keep paging from nextOffset. Each row is one business with only its populated fields, e.g. name, category, phone, email, website, address, city, state, postal_code, country_code, rating, reviews, business_status, company_facebook/instagram/linkedin/x/youtube, location_link, place_id and _status (found -> extracted -> enriched). Page with offset/nextOffset until hasMore is false. For a spreadsheet of every row use download_export instead of paging through thousands of rows.

Save a finished scrape as a spreadsheet file on this computer and return its path. The API serves the file itself (authenticated), so this tool downloads it rather than returning a link. Only works once the scrape status is done. The file uses the full column layout (every column, blanks where unknown). Files are never overwritten: an existing name gets a -1, -2... suffix.