scrape_markdown

io.github.vanakenj45/x402-agent-api · Verify this server

Use it when an agent needs to read a web page, article, documentation, PDF, blog post, product or pricing page, news story or RSS feed. Returns the main content as clean Markdown ready for an LLM: navigation, ads, footers and sidebars removed (or `mode: "full"` for the whole page), real tables as Markdown tables, code blocks with their language, math as TeX, the real (not lazy-loaded placeholder) images, absolute links without same-page anchors, and no needless escaping. Also returns metadata from meta tags and JSON-LD (description, author, published and modified time, language, site name, canonical URL, image, schema.org type), the HTTP status, word and token counts, and optionally the page's links. PDFs come back as text by page (up to 100 pages, 15 MB; no OCR), RSS/Atom feeds as item lists, JSON pretty-printed, and JavaScript-built pages that embed their content as data (JSON-LD articleBody, Next.js) are read from it. Long pages are returned in parts of up to 100,000 characters: pass `next_offset` back as `offset`; `strip_link_urls` saves tokens. Bot checks ("Just a moment...") and pages with no readable text answer 422 and are not charged; JavaScript is not executed. No account or API key. You are only charged when a result is returned: invalid input (400) and upstream failures (4xx/5xx) are not settled. Costs $0.002 USDC per call via x402. Paid per call with x402 inside MCP (see the server instructions).