MCP Connector · Claude

Give Claude web scraping powers

Connect Ultimate Web Scraper to Claude or Claude Code and scrape whole websites, query the results and run automations — right from the conversation.

ClaudeClaudeUltimate Web Scraper
Scrape the entire catalogue of shop.example.com — every product and variant.
Claude
Shopify Extractor · 412 products, 1,180 variants

Pulled the whole store — one row per variant:

ProductPrice
Oak Platform Bed$1,290
Linen Panel Bed$980
Walnut Storage Bed$1,540
1,180 rows · 7 columnsView table →

Works with MCP-compatible AI apps

ClaudeChatGPTCursorPerplexityHermesOpenClaw
Trusted by teams worldwide
80,000+Professionals
10M+Pages collected
4.8Chrome Store
Set up in about a minute

Connect Claude in 3 easy steps

1

Install the extension

Add Ultimate Web Scraper to Chrome — free. The Connect Claude button lives inside it.

2

Connect Claude

Open Settings → Connect Claude. It signs you in and hands you one link to paste into Claude.

ClaudeSettings → Connect Claude

Part of the paid cloud plans.

3

Just ask

Ask Claude to scrape a website. Claude runs the scrape and hands back a clean table you can export.

Copy it, paste it into Claude.

Using Claude Code? It’s one command → Cursor or another AI app? See the MCP page →

What you can ask for

Scrape in plain English

Tell Claude what you want, get a table back. It picks the tools and runs the scrape — no selectors, no code.

ClaudeClaudeUltimate Web Scraper
Scrape the entire catalogue of [your-store.com] — every product and variant.
Tools for scraping

Scraping tools your agent can use

Scrape Shopify stores, product pages, emails, phone numbers, social profiles and Google Maps listings — or map entire sites from their sitemaps.

2,000 pages

Page Extractor

create_extraction · product_pages

Extract name, price, availability, brand, images and ratings from a list of product URLs. Works on products, articles, job and event pages too.

Shopify CSV export

Shopify Extractor

extract_shopify_store

Extract an entire Shopify store, or just the collections you name, into one row per variant — price, SKU, options, images, availability.

10,000 sites

Email Extractor

create_extraction · emails

Scan landing pages from a URL list for email addresses. Optionally follows internal links a level deeper to reach contact pages.

10,000 sites

Social Link Scanner

create_extraction · social_links

Scan landing pages from a URL list for links to social profiles, across all eight platforms.

LinkedInXFacebookInstagramYouTubeTikTokGitHubPinterest
2,000 listings

Google Maps Scraper

create_extraction · google_maps

Pull name, rating, address, phone, website and opening hours from a list of Google Maps listings.

2,000 pages

Phone Number Extractor

create_extraction · phone_numbers

Scan pages from a URL list for phone numbers, collected beside the page each one came from.

25 credits flat

Sitemap Explorer

discover_sitemap

Map every page on a site from its own sitemap, grouped into sections, then pick which ones to scrape. No URL list needed.

Free

Website Analyzer

analyze_website

Check any site before you scrape it — detects the platform, finds the sitemap, picks the approach that works.

Built in the extension

Your saved scrapers

run_automation

Run the point-and-click scrapers you built in the extension — on demand, or on a daily schedule.

Plus it runs any point-and-click scraper you’ve built in the extension, keeps any job on a daily schedule, and answers “how do I…?” straight from our docs.

Side by side

Why connect us to Claude

On its own, Claude reads a handful of pages before it's blocked or the chat fills up. Connected to us, it scrapes thousands — real browsers, proxies and a clean table back.

Without

ClaudeClaudeNo tools connected
Scrape all the products on store.com
Claude
store.com/productsPage 1 only
store.com/p/1042403 blocked
store.com/p/1043Needs JavaScript

I could only reach a few pages — most were blocked or came back empty. You’d need to paste the rest in yourself, a handful at a time.

  • Reads a handful of pages before the conversation is full
  • One page at a time, in the chat, while you wait
  • Pages that build themselves with JavaScript come back empty
  • Hits rate limits and anti-bot blocks from one address
  • Results are text in a chat — gone when you close it
  • To analyse it, you paste the data back in and hope it fits
  • Want it again tomorrow? Ask again from scratch

WithUltimate Web Scraper

ClaudeClaudeUltimate Web Scraper
Scrape all the products on store.com
Claude
Sitemap Explorer · mapped 2,431 pages
Product details · 186 product URLs

Scraped all 186 product pages into one table.

186 rows · 6 columnsView table →
  • Thousands of pages in a single job — up to 10,000 sites for contact data
  • Runs on parallel cloud browsers — close the tab, it keeps going
  • Real browsers that render the page the way you'd see it
  • Proxies and anti-bot handling built in
  • Results land in a saved table you can filter, export and re-run
  • Ask questions of a 100,000-row table without it entering the chat
  • Put it on a daily schedule and the table stays fresh

You stay in charge: a new scrape always shows its price before it runs, and you can connect read-only so it can look but never scrape or change anything.

Cloud scraping engine

Built to handle scale

Your AI does the asking — our cloud does the scraping. Every job runs on our infrastructure, not your machine.

Ultimate Web ScraperUltimate Web ScraperCloud5 running
store.com
1,204
shop.example
supplier.io
612
catalog.net
2,890

Parallel browsers

Many sites scraped at once.

Proxies, built in

ISP & residential, any country.

Anti-bot handling

JS rendered, blocks cleared.

Long, unattended runs

Up to 24 hours a job.

Cloud-only

Nothing to host or keep awake.

Claude & Claude Code

How to connect Claude

Claude

Claude (web and desktop)

Guided, sign-in based. No key to create, nothing to keep safe.

  1. 1Copy one link — the extension's Connect Claude page hands it to you.
  2. 2In Claude, open Settings → Connectors and click Add custom connector.
  3. 3Paste the link, click Connect, and sign in when prompted. Pick your workspace and your access level — done.

About a minute, start to finish.

Using Cursor or another MCP-compatible app? It connects with an access token instead — everything’s on the MCP page.

Common questions

MCP (Model Context Protocol) is an open standard that lets an AI assistant use other apps on your behalf. Ultimate Web Scraper runs an MCP server, so once you connect it, Claude can use our scraping tools the same way it uses its own. You don't need to understand any of it to use it — you paste one link and sign in.

Stop copy-pasting. Start asking.

Install the free extension, connect Claude once, and your next scrape is a sentence away.

Free to install · 80,000+ users · 4.8★ on the Chrome Web Store

Claude is a trademark of Anthropic, PBC. Ultimate Web Scraper is an independent product and is not affiliated with, endorsed by, or sponsored by Anthropic. All other product names and logos are trademarks of their respective owners, used for identification only.