Scrapi

If you've ever needed Claude to actually read a webpage instead of hallucinating about it, this is the fix. Scrapi exposes two tools: fetch a URL as clean Markdown (preserving structure) or plain text, with metadata like title and publish date. It handles JavaScript rendering, strips ads and navigation cruft, and bypasses basic anti-bot measures. Runs over stdio via npx or streamable HTTP if you don't want Node.js on the client. Free tier gives you 500 credits monthly. Built by a team running 1,900+ production scrapers, so the anti-bot logic is battle tested, not wishful thinking.