Oxylabs MCP: scrape, crawl and search the web from your AI app

Add the Oxylabs Web Scraper API to your AI app

1. 1Click Connect Oxylabs free. There's no sign-in, so its tools are ready at once.
2. 2All ten tools fetch data. `ai_browser_agent` goes further, navigating a site and taking actions on it, so switch it off if you only want pages read, not clicked through.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to scrape the first page of Amazon results for a product search, then open Activity to see the `amazon_search_scraper` call.

Web data jobs for Claude or Cursor

• Get the content of any page with `universal_scraper`, with browser rendering when a page needs it.
• Crawl a site from a starting URL with `ai_crawler`, or list its URLs with `ai_map`.
• Pull Google Search results with `google_search_scraper`, with locale and geolocation settings.
• Scrape Amazon search results and product pages with `amazon_search_scraper` and `amazon_product_scraper`.

Know what your AI apps scraped

• Switch off `ai_browser_agent`, or any other Oxylabs tool, and your AI apps can no longer see or call it.
• Policies check each call, so a URL carrying a token in its query string can be blocked.
• Activity records every scrape, crawl and search your team's AI apps run through Oxylabs.

What you get with Oxylabs and ContextGate

• Your AI apps can use OxylabsClaude, Cursor, ChatGPT and other AI apps reach Oxylabs through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Oxylabs tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Oxylabs tools

Examples of what your AI apps can do in Oxylabs. You'll see the exact list of tools after you connect it.

• ai_crawlerTool useful for crawling a website from starting url and returning data in a specified format. Schema is required only if output_format is json, csv or toon. '
• ai_scraperScrape the contents of the web page and return the data in the specified format. Schema is required only if output_format is json or csv. 'render_javascript' i
• ai_browser_agentRun the browser agent and return the data in the specified format. This tool is useful if you need navigate around the website and do some actions. It allows n
• ai_searchSearch the web based on a provided query. 'return_content' is used to return markdown content for each search result. If 'return_content' is set to True, y
• generate_schemaGenerate a json schema in openapi format.
• ai_mapTool useful for mapping website's URLs.
• universal_scraperGet a content of any webpage. Supports browser rendering, parsing of certain webpages and different output formats.
• google_search_scraperScrape Google Search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output for
• amazon_search_scraperScrape Amazon search results. Supports content parsing, different user agent types, pagination, domain, geolocation, locale parameters and different output for
• amazon_product_scraperScrape Amazon products. Supports content parsing, different user agent types, domain, geolocation, locale parameters and different output formats. Supports Ama