Pull products, prices, reviews, images and contacts out of any site with a single click — or hand the job to your AI agent and get back a finished table.
Same engine underneath — pick the workflow that fits the job.
Hover a list on the page, click it, and every row lands in an editable table in Chrome's side panel — ready to export.
Connect Claude, Cursor or any MCP-capable app once. After that, just ask in plain English — the scrape runs and a table comes back.
Hand a scrape to cloud browsers. It runs at volume, on a schedule, from the country you pick — and delivers fresh data on its own.
Every column is dynamically typed and parsed on extraction — prices, images, ratings, links, and contact tags. Clean data in browser, sort, filter, and export in one click.
| # ID | Product Name | Category | Price | Rating | Stock Status | Extracted URL |
|---|---|---|---|---|---|---|
| 001 |
👟
Trail Runner Pro GTX
|
Footwear | $149.00 | ★ 4.9 (420) | In Stock | /products/trail-runner-gtx |
| 002 |
🚴
Apex City Commuter E-Bike
|
Cycling | $899.00 | ★ 4.8 (184) | In Stock | /products/apex-commuter-ebike |
| 003 |
☕
Artisan Ceramic Pour-Over Set
|
Kitchenware | $42.50 | ★ 5.0 (92) | In Stock | /products/ceramic-pour-over |
| 004 |
💡
Nordic Minimalist Oak Desk Lamp
|
Home Office | $76.00 | ★ 4.7 (311) | In Stock | /products/nordic-desk-lamp |
| 005 |
🧥
Featherlight 850 Alpine Down Jacket
|
Apparel | $210.00 | ★ 4.9 (614) | In Stock | /products/featherlight-down-jacket |
Currency, ratings, image URLs, SKU identifiers, and timestamps are automatically recognized and typed without manual mapping.
Drop redundant columns, trim whitespace, deduplicate rows, and run regex transforms before your data leaves your browser.
Export directly to CSV, Excel (.xlsx), structured JSON, or sync straight into Google Sheets or your clipboard in milliseconds.
Connect once via Model Context Protocol (MCP). Your AI agent handles the extraction, cleans the schema, and writes directly into your database or spreadsheet — using natural language.
Traditional AI web scrapers dump megabytes of messy raw HTML into your chat context window, burning through your tokens and hitting token limits within seconds.
Urban Web Scraper offloads the DOM execution, anti-bot handling, and parsing to high-performance engines, returning only the finalized, structured table your agent actually needs.
Name, price, SKU, variants, availability, and high-res images for every product URL.
Shopify, WooCommerce, Magento, Amazon — pull entire inventories in a single prompt.
“Find all product pages on this store” — maps the domain and extracts targeted slices.
Verified emails, phone numbers, and executive social profiles across company directories.
Business names, ratings, physical addresses, opening hours, and review sentiment.
Run filters, sums, joins, and aggregations on 100k+ rows without loading them into memory.
“Drop empty columns, merge address fields, strip HTML tags.” Executed instantly.
“Re-run yesterday's competitor price monitor every day at 8 AM.” Automated end-to-end.
Stream directly into Google Sheets, Airtable, Neon Postgres, webhook endpoints, or CSV.
Use our 1-click prompt to let your AI configure itself automatically, or copy-paste ready configurations for Claude Desktop, Cursor, and any MCP environment.
Copy this single prompt and paste it into any AI assistant. Your agent will inspect your local files and set up the connection automatically:
Configure the Urban Web Scraper MCP server for my environment: - Server Name: urban-web-scraper - Server URL (SSE): https://api.urbanqode.com/mcp/sse - Stdio Command: npx -y urban-scraper-mcp - Target Tools: * urban_scrape_page_markdown: extract clean markdown & structured metadata * urban_extract_list: extract repeating tables and card grids into typed 2D arrays * urban_extract_shopify: extract full catalogs, variants, SKUs, inventory & pricing * urban_extract_contacts: extract verified emails, phones, and social links * urban_crawl_sitemap: discover and filter URLs via sitemaps & robots.txt * urban_verify_license: check Pro license status and device bindings - License Key: [PASTE YOUR PRO KEY HERE, OR PASS VIA URBAN_SCRAPER_LICENSE_KEY] Inspect my local MCP configuration file (e.g. claude_desktop_config.json or .cursor/mcp.json) and configure this server now.
Urban Web Scraper
{
"mcpServers": {
"urban-web-scraper": {
"command": "npx",
"args": ["-y", "urban-scraper-mcp"],
"env": {
"URBAN_SCRAPER_LICENSE_KEY": "YOUR-PRO-KEY-HERE"
}
}
}
}
{
"mcpServers": {
"urban-web-scraper": {
"url": "https://api.urbanqode.com/mcp/sse",
"headers": {
"x-license-key": "YOUR-PRO-KEY-HERE"
}
}
}
}
{
"mcpServers": {
"urban-web-scraper": {
"url": "https://api.urbanqode.com/mcp/sse",
"headers": {
"x-license-key": "YOUR-PRO-KEY-HERE"
}
}
}
}
npx -y urban-scraper-mcp --key YOUR-PRO-KEY-HERE
https://api.urbanqode.com/mcp/sse?key=YOUR-PRO-KEY-HERE
Pages render for real — JavaScript runs, lazy content loads, and consent walls get handled on the way in.
Keep a Google Sheet current on every run, or push results to a webhook and let your own stack take it from there.
Every ten minutes, every morning, or once a month — your competitor price sheet updates before you wake up.
Add one step to a page extraction and every row carries its title, description, image, author and canonical URL.
Name downloaded files after several columns at once — Brand, then Name, and they save as Brand_Product.
Browse a site as a tree and send the pages you pick straight to the extractor — no URL list to build first.
From solo analysts to enterprise engineering teams — here is why they keep Urban Web Scraper pinned to their toolbar.
“The side panel picker is pure magic. I hovered a multi-variant Amazon store page, clicked once, and all 45 variants with prices, ASINs, and high-res image URLs populated into an editable table in seconds. Replaced our team's $300/mo scraping SaaS subscription.”
“Connecting Urban Web Scraper to Claude Desktop via MCP completely transformed our market research. I just prompt 'scrape every pricing plan across these 20 competitor domains' and I get back a formatted Google Sheet in under 3 minutes. Zero HTML spam in my chat.”
“Most scrapers stall the second Cloudflare or dynamic JavaScript pagination shows up. Urban Web Scraper runs in real Chromium, handles lazy loading seamlessly, and never crashes. We've built outbound lists of over 150k leads with zero friction.”
“The multi-tab concurrent scraper is ridiculously fast. Being able to unbind and transfer license keys between my MacBook and workstation through the Customer Portal is effortless. Best $50 our ecommerce team spent this year.”
“The in-browser regex cleaning, deduplication, and column auto-typing saves me at least an hour per job. I don't need to write one-off Python BeautifulSoup or Playwright scripts anymore for fast client turnarounds.”
“We work under strict enterprise compliance rules. Checking the browser network tab confirmed it: local extractions never touch any third-party server. Perfect for sensitive B2B supplier price benchmarking and competitive audits.”
Two intuitive ways to extract clean data. Neither requires writing a single line of code.
Point at any list or table on a webpage, click it, and export clean data directly in your browser's side panel.
Hook into Claude Desktop, Cursor, or any MCP client. Scrape whole websites with a single plain English prompt.
claude mcp add urban-scraper https://api.urbanqode.com/mcp
No Chrome Web Store wait — run the extension immediately in any Chromium browser.
Click Download Extension to get urban-web-scraper.zip. Right-click and extract it anywhere on your computer.
In Chrome, Edge, or Brave, navigate to chrome://extensions. In the top-right corner, toggle Developer mode on.
Click the Load unpacked button in the top left and select the unzipped urban-web-scraper folder. The extension appears in your toolbar!
No. You point at what you want on the page and click it — there are no selectors to write and nothing to install beyond the extension. Most people have their first export within minutes.
Not when you scrape locally — results sit in your browser until you export them. Only jobs you explicitly send to the cloud run on our infrastructure, in a workspace only you can see.
Your agent connects to your cloud workspace over MCP, where the scraping tools and your result tables live. You connect once by pasting a link; from then on you ask for data in plain English.
The extension installs free and local extraction is unlimited. Power features, multi-tab scraping and unlimited exports are part of our simple one-time lifetime plans ($25 Pro, $50 Pro+, or custom Team) — see the pricing page for details.
Yes — it scrapes the page as your browser renders it, logged-in sessions included. Some heavily protected sites are better handled by the cloud's proxies.