Happy slice of mcp pizzaMCP.pizza

WebReaper

MCP.Pizza Chef: alex-on-ai

WebReaper is a single small program that fetches a page and hands back tidy, readable text instead of raw page code. It can walk an entire site, pull out just the fields you name, and quietly switch to a real browser when a site tries to block it. Two versions plug into assistants: one runs on your own machine for Claude Desktop and Cursor, the other runs at a web address for tools like n8n. Naming fields in plain English needs a paid model key.

Data
Web/Research

Use This MCP server To

Turn a long article into clean readable text Pull every blog post address from a company website Collect product names and prices across a whole store Read a page that normally blocks automated visitors Save a research page as a file I can reuse Gather several pages at once for a summary

README

logo

WebReaper

NuGet CI License: MIT

AI-native web scraper. Single binary with a bundled Claude Code skill.

Built by HighCraft.io.

Install

macOS / Linux (Homebrew):

brew install alex-on-ai/webreaper/webreaper

Any POSIX shell (install.sh):

curl -fsSL https://raw.githubusercontent.com/alex-on-ai/WebReaper/master/scripts/install.sh | sh

.NET library:

dotnet add package WebReaper

Windows binaries are on the GitHub Releases page; winget and Scoop are on the v10.1 roadmap.

Updating: brew upgrade webreaper (Homebrew), or re-run the install.sh line with --upgrade appended (| sh -s -- --upgrade), or dotnet add package WebReaper (library). When a newer release exists, scrape / crawl / map print a one-line upgrade hint on stderr (interactive terminals only, never in a pipe or CI); disable that check with WEBREAPER_NO_UPDATE_CHECK=1.

30-second demo

$ webreaper scrape https://news.ycombinator.com
# Hacker News

- [Show HN: ...](https://news.ycombinator.com/item?id=...)
- [Ask HN: ...](https://news.ycombinator.com/item?id=...)
...

$ webreaper init
Wrote WebReaper Agent Skill to .claude/skills/webreaper/SKILL.md

Try it out:
  webreaper scrape https://example.com
  webreaper map https://example.com

After webreaper init, the next Claude Code session picks up the skill and routes scraping intents ("give me the markdown of X", "what blog posts are on Y", "scrape the top 5 articles") to webreaper automatically.

WebReaper FAQ

Which apps can use it?
Claude Desktop, Cursor, Copilot Studio and other assistants that run local tools, plus n8n over a web address.
Do I have to pay for anything?
The tool is free and MIT licensed; only the smart field-picking features need a paid model key.
How hard is setup?
You install one small program with Homebrew or a single install command, then point your assistant at it.
Can I use this to read a site that keeps blocking me?
Yes — it notices the block and retries through a real browser, then a stealth browser, on its own.
Will it hand back junk pages when a site blocks it?
No — a page still blocked at the last attempt is dropped rather than passed along as a result.
Do I need Docker?
Only for the web-address version; the normal one is a single file of about 12 MB you drop on your computer.