// Docs

Turn websites into LLM-ready markdown

Pagelyte is the context API to search, scrape, and interact with the web at scale.

MCP

Official MCP server so agents in Cursor, Claude, Windsurf, and other MCP-compatible tools can search, scrape, and interact with the web directly.

CLI

npx -y pagelyte-cli@latest init --all --browser

Build with AI

Agent onboarding: email team@pagelyte.xyz for an API key. 1,000 free credits / month. No card.

Playground

Try endpoints from this docs page (client demo). Full playground access is arranged by email.

Search

Send a query and Pagelyte returns relevant results from across the web, each with full-page markdown already included. It's one call to go from a question to usable content.

Scrape

Give Pagelyte a URL and it returns clean, structured content — markdown, HTML, screenshots, metadata, or extracted data via a schema. It handles JavaScript rendering automatically.

Interact

Operate web pages — clicking, filling forms, navigating multi-step flows. Useful when information is behind pagination or a sequence of actions.

Monitor

1 credit per page per check.

Parse

Pass a JSON schema to scrape and get structured data matching your shape.

Map

Discover URLs across a website.

Crawl

1 credit per page. Extract entire sites.

Agent

Preview: 5 daily runs free. Dynamic pricing.