Labsco
MCP SERVER · OFFICIAL PROJECT

Oxylabs

by oxylabs

Pull clean, structured data off any site — including JavaScript-heavy and geo-restricted pages — with CAPTCHAs and proxies handled for you.

Site Crawling & Scraping InfrastructureOfficial source
Summary
Two ways to scrape, and you pick per job.

The split is the point: the Web Scraper API tools are for when you know the URL and want raw or parsed output, and the AI Studio tools are for when you describe what you want and let a crawler or browser agent go find it. You can hold both sets of credentials and reach for whichever fits, or hold just one and use only that half.

What it is

Oxylabs' official server, exposing two toolsets you can use together or apart: four Web Scraper API tools for direct scraping, and six AI Studio tools for prompt-driven extraction, crawling and a browser agent. It runs from PyPI over stdio, or as Oxylabs' hosted server with no install.

What you get
  • universal_scraper fetches any URL with optional JavaScript rendering, geo-targeting, and Markdown, HTML or links output
  • google_search_scraper and amazon_search_scraper pull search-result pages with parsing into structured JSON, pagination, user-agent type, domain, geolocation and locale, and Amazon-specific parameters like category id and merchant id
  • amazon_product_scraper reads an individual product page, including auto-selecting a variant for more accurate pricing
  • ai_scraper extracts a page into JSON, CSV, Markdown or TOON, with a schema required only for the structured formats
  • ai_crawler walks a site from a starting URL guided by a prompt and collects data across pages, with return_sources_limit to cap how many it follows
  • ai_browser_agent drives a real browser from a prompt — navigating, clicking links, filling forms, scrolling — and returns the result in your chosen format
  • ai_search runs a web search and, with return_content, hands back the Markdown of each result so you skip a separate scrape
  • ai_map lists a site's URLs filtered by keywords or a prompt, and generate_schema writes the OpenAPI-format JSON schema the structured AI tools expect
  • CAPTCHA handling and proxy rotation across 195+ countries sit behind all of it, so a blocked or geo-restricted page still returns data
Requirements

At least one Oxylabs credential, and which one depends on the tools you want: the Web Scraper API tools use OXYLABS_USERNAME and OXYLABS_PASSWORD (a one-week free trial is available), and the AI Studio tools use OXYLABS_AI_STUDIO_API_KEY (1,000 free credits). Use the hosted server at https://mcp.oxylabs.io/mcp with those credentials in request headers, or run it locally from the oxylabs-mcp PyPI package over stdio, which also needs the uv package manager.

Setup effort

One command plus a key — uvx oxylabs-mcp, then supply credentials