MCP Tool Reference

Every MCP tool a connected AI agent can use in Ultimate Web Scraper — querying tables, cleanup, exports, automations, site discovery, and Shopify extraction.

A connected AI agent works through a set of named tools — you ask in plain language, the agent picks the right one, and most clients show each call as it happens. Here's every tool, grouped by the access level that unlocks it; a read-only connection only gets the first group.

Reading & analysis — every connection

ToolWhat it does
get_workspace_infoYour plan, credit balance, and the connection's access level
list_tablesLists your result tables, grouped by the automation that produced them
get_tableOne table's columns, row count, and a small sample of rows
query_tableFilters, aggregates, groups, and sorts a table of any size — the full table never enters the conversation
export_tableGenerates a download link in CSV, JSON, or Excel. Tables produced by a Shopify extraction can also export as a re-import-ready Shopify product CSV
list_automationsYour automations, their schedules, and their status
list_runsThe run history of an automation
get_runA run's live progress and row count so far, plus links to watch it or open the results table
search_docsSearches this documentation to answer product questions
get_docs_pageReads a single docs page in full
list_docsThe documentation's table of contents

Cleaning & operating — full access

ToolWhat it does
run_automationStarts an automation run
stop_runStops a run in progress
export_table_to_google_sheetsSends a whole table to a new spreadsheet in your Google Drive (uses the Google Sheets integration)
update_columnRenames a column or changes its type
delete_columnsDeletes columns you don't need
merge_columnsMerges 2–5 columns into one (street + city + zip → Address)
delete_rowsPermanently deletes the rows matching a filter — it reports the match count first and deletes only after you confirm
deduplicate_rowsRemoves duplicate rows, keeping the first occurrence — with the same count-first confirmation

Extracting — full access

ToolWhat it does
analyze_websiteFree first look at any site you want scraped: identifies the platform, checks for a sitemap, and returns the extraction strategies that apply
create_extractionStarts a zero-configuration extraction — product pages, emails, social links, phone numbers, or Google Maps — from pasted URLs or a table column. Returns a credit estimate first and runs only after you confirm
discover_sitemapMaps a site's URLs into a grouped overview — the starting point for "scrape this whole site" or "just the winter collection"
select_sitemap_urlsFilters a discovery — by group, search term, or exclusions — into a URL table that feeds straight into create_extraction
list_shopify_collectionsLists or searches a Shopify store's collections by name
extract_shopify_storeExtracts a Shopify store's catalogue — the whole store or chosen collections — as one clean row per product variant. Estimates credits and asks before running

Ready-made prompts

The connection also includes starter prompts — one-click workflows like "discover and scrape a site", "scrape a Shopify store", or "clean up a table" — that appear in Claude's connector menu and as slash commands in Claude Code. Only ones your access level can run are shown.

Credit & safety behavior

  • Reading, querying, cleaning, and exporting consume no credits. Site discovery uses a small flat credit charge, only when it actually finds URLs.
  • Anything that spends credits or deletes data happens in two steps: the agent shows you a cost estimate or a match count first, and nothing runs until you confirm.
  • Oversized results are never dumped into the chat — the agent is asked to narrow its query instead.

On this page