Web scraping MCP server for Claude, Cursor, Windsurf & AI agents — scrape any site, extract structured data, take screenshots. Anti-bot bypass, proxy rotation, authenticated scraping.
-
Updated
Aug 13, 2026 - TypeScript
Web scraping MCP server for Claude, Cursor, Windsurf & AI agents — scrape any site, extract structured data, take screenshots. Anti-bot bypass, proxy rotation, authenticated scraping.
OCR-free receipt & invoice parsing: runs the Donut vision model locally to extract line items, tax, and totals as structured JSON, storing every raw image and extraction in Backblaze B2 (S3-compatible) — no OCR step, no database, no second API key.
Add a description, image, and links to the structured-data-extraction topic page so that developers can more easily learn about it.
To associate your repository with the structured-data-extraction topic, visit your repo's landing page and select "manage topics."