Happy slice of mcp pizzaMCP.pizza

PyScrappy

MCP.Pizza Chef: mldsveda

Point it at a link and your assistant gets back tidy text, tables, images, and links instead of raw page code. Beyond plain links it carries ready-made helpers for Wikipedia, news feeds, stock quotes, weather, crypto prices, currency conversion, word definitions, and searches across YouTube, GitHub, Hacker News, books, job listings, Amazon, Newegg, and IKEA. It works with Claude Desktop, Claude Code, Cursor, Cline, and Goose. Most of it needs no key; movie lookups need a free OMDb one.

Data
Web/Research

Use This MCP server To

Read a long web page and summarise it for me Pull a table off a page into something I can use Check the current price of a stock or a coin Get today's headlines from a news site I follow Search job listings or products and compare what comes back Look up a Wikipedia article and pull out one section

README

PyScrappy: Python web scraping toolkit + MCP server for AI agents

Python 3.9+ PyPI Latest Release License: MIT Downloads Glama quality Documentation MCP Toplist

PyScrappy is an AI-native web scraping toolkit that turns websites into structured, LLM-ready data. Use it as a Python library or expose it as an MCP server for AI agents.

📖 Documentation: pyscrappy.vercel.app

Key features

  • Generic scraper — give it any URL, get back structured text, links, images, tables, and metadata
  • LLM-ready output — .to_markdown() turns any result into clean Markdown; also .to_json() and .to_dataframe()
  • MCP server — expose the scrapers as tools for AI agents (Claude, Cursor, local LLMs, …)
  • JS rendering — optional Playwright backend for JavaScript-heavy sites
  • Custom selectors — pass CSS selectors to extract exactly what you need
  • Concurrent scraping — scrape_many / scrape_all run scrapes in parallel
  • Proxy & scraping-API support — route through a proxy or ScraperAPI/ScrapeOps for blocked sites
  • Retry & rate-limiting — built-in exponential backoff and per-domain rate limiting
  • Type-safe — full type hints, py.typed marker
  • 20+ built-in scrapers — Wikipedia, IMDB, stocks, news, GitHub, Amazon/IKEA, YouTube, and more

Installation

pip install pyscrappy

Optional extras:

PyScrappy FAQ

Which apps does it work in?
Claude Desktop, Claude Code, Cursor, Cline, and Goose. It can also drive a local model through Ollama with no host app in between.
Do I need an account key?
Not for most of it. Movie lookups need a free OMDb key, and routing through a paid scraping service is optional.
How hard is setup?
One Python install command, then a single line registers it with Claude Code, or you paste a short block for Claude Desktop.
Can I use this to pull a table off a web page?
Yes. It returns tables, plain text, links, images, and page details, and can hand them over as clean Markdown.
Does it work on pages that build themselves after loading?
Yes, with the optional browser add-on installed, which loads the page properly before reading it.
What if a site blocks it?
You can route requests through a proxy or a scraping service, and it waits and retries when a site pushes back.