Documentation has been updated: see help center and changelog in one place.
Explore
LogoLogo
Oxylabs dashboardProduct
  • Documentation
  • Help center
  • Changelog
  • Help center
  • Most popular questions
    • Getting started: Proxy Solutions
    • Getting started: Web Unblocker
    • Getting started: Web Scraper API
    • Custom pricing or a free trial
    • Restricted targets: Proxy Solutions and Web Scraper API
    • What is your refund policy?
    • How do I choose the right product?
  • Getting started
    • Start using Residential Proxies
    • Start using Mobile Proxies
    • Start using ISP Proxies
    • Start using Datacenter Proxies per IP
    • Start using Dedicated Datacenter Proxies
    • Start using Web Scraper API
    • Start using Web Unblocker
  • Proxies integrations with third-party tools
  • Where can I find setup tutorials?
  • Products & features
    • How can I whitelist IPs?
    • How to set up limitations
    • Location settings for Proxies
    • Supported protocols
    • Public API
    • How to use session control
    • Web Scraper API features
    • Web Scraper API integration methods
    • My usage statistics
    • Countries Oxylabs Proxies cover
    • Can I buy products without having to contact you?
    • Playground to test Web Scraper API
    • Dedicated parsers
    • Is web scraping legal?
    • Features that can assist with web scraping tasks
    • How to select your proxy location
    • YouTube Downloader for AI projects
    • What data can I extract with the YouTube Downloader?
    • What solution should I use for building LLMs?
    • How can I define browser instructions automatically?
    • What actions can I automate with Browser instructions?
    • What is the fair usage policy for Dedicated Datacenter IPs?
    • Examples on how to use OxyCopilot
  • Can I use pre-made OxyCopilot prompts for my own projects?
  • Troubleshooting
    • Response codes for Proxies
    • Response codes for Web Scraper API
    • How do I use a cURL command?
    • I can’t access my account
    • Where can I find my scraping job ID?
    • Does Web Unblocker have JavaScript rendering?
    • From what targets can I get parsed data?
    • What targets can I scrape with a Web Scraper API?
    • How to use the Endpoint Generator
  • Billing & payments
    • How does Web Scraper API pricing work?
    • How does Web Unblocker pricing work?
    • How to cancel a subscription?
    • Do I need to sign a contract before purchase?
    • What forms of payment do you accept?
    • How does your billing cycle work?
    • Are there any additional fees I should be aware of?
    • Can I get a refund for unused traffic?
    • What are Oxylabs pricing plans' limitations?
  • Dashboard
    • How to transfer team ownership
    • How to invite team members
    • Web Scraper API 101: Navigating the dashboard
    • Proxies 101: Navigating the dashboard
    • IP Replacement
  • Free Datacenter Proxies
    • Set up free Datacenter Proxies
    • Free Datacenter IPs: troubleshooting guide
    • Can I choose the locations for my free IPs, or are they assigned automatically?
    • Are there limits on how many connections or threads I can run at the same time?
    • Can I replace my free Datacenter IPs with new ones?
    • Can I use IP whitelisting for authentication when using the free Datacenter IPs?
    • Is the 5 GB traffic limit per IP or shared across all 5 IPs?
    • If I upgrade to a paid plan, can I go back to the free one later?
    • What is the fair usage policy for Free Datacenter IPs?
    • If I upgrade to a paid plan, will I keep the same IPs?
  • Data for LLMs
    • Do you deliver data in an LLM-optimized format?
    • Do I have to manually format scraped data for AI workflows?
    • What is Model Context Protocol (MCP), and how does it benefit Web Scraper API usage?
    • How do I use Model Context Protocol (MCP) with Web Scraper API?
    • How does Model Context Protocol (MCP) standardize data for LLMs?
Powered by GitBook
On this page

Was this helpful?

  1. Data for LLMs

Do you deliver data in an LLM-optimized format?

PreviousIf I upgrade to a paid plan, will I keep the same IPs?NextDo I have to manually format scraped data for AI workflows?

Last updated 1 day ago

Was this helpful?

Yes, the Model Context Protocol (MCP) support is a built-in feature of our . The MCP process transforms raw HTML into formats that Claude, GPT, and other models can immediately understand. No manual reformatting is required.

🛠️ MCP acts as a wrapper that structures the Web Scraper API’s output with context, metadata, and instructions, ensuring compatibility with LLMs.

Web Scraper API