PyScrappy MCP server
Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-fingerprint stealth to bypass anti-bot filters, CSS/XPath parsing, and 24 built-in scrapers, clean, structured, LLM-ready data from any URL.
What PyScrappy does
Summarised from the project README; check the repository for the latest details.
Features
- Generic scraper — give it any URL, get back structured text, links, images, tables, and metadata
- LLM-ready output — `.tomarkdown()` turns any result into clean Markdown; also `.tojson()` and `.todataframe()`
- 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
- Chainable `Selector` — navigate HTML directly with CSS/XPath, `findall`, `findbytext`, and `findsimilar` (Scrapy/BeautifulSoup-style)
Repository: mldsveda/PyScrappy
Website: https://pyscrappy.vercel.app
Stars: ★261
Language: Python
Last updated: 2026-09-25
aiai-agentsecommerce-scrapperfood-scrapperhacktoberfesthacktoberfest-acceptedimage-scrappermcpmcp-servernews-scrapperpyscrappypythonsocial-media-scrappersong-scrapperstock-scrapperweb-scrappingwikipedia-scrapper
Website: https://pyscrappy.vercel.app
Stars: ★261
Language: Python
Last updated: 2026-09-25
aiai-agentsecommerce-scrapperfood-scrapperhacktoberfesthacktoberfest-acceptedimage-scrappermcpmcp-servernews-scrapperpyscrappypythonsocial-media-scrappersong-scrapperstock-scrapperweb-scrappingwikipedia-scrapper
How to install PyScrappy
No install config was found in this README. See the repository for setup steps, then follow our guides for Claude Desktop, Cursor or VS Code.
Featured in: Best MCP servers for web scraping
Listed on Socketlist – add this badge to your README:
Maintain this project? Get it featured for free during launch →
Related Web Search & Scraping MCP servers
gpt-researcher by assafelovic · ★30100
An autonomous agent that conducts deep research on any data using any LLM providers
Web Search & Scraping
An autonomous agent that conducts deep research on any data using any LLM providers
Web Search & Scraping
Douyin_TikTok_Download_API by Evil0ctal · ★20643
🚀 抖音、TikTok 数据采集与无水印视频下载 API，自托管，支持 MCP 调用与 Docker 一键部署。| Self-hosted TikTok & Douyin scraper and no-watermark video downloader — async RES
Web Search & Scraping
🚀 抖音、TikTok 数据采集与无水印视频下载 API，自托管，支持 MCP 调用与 Docker 一键部署。| Self-hosted TikTok & Douyin scraper and no-watermark video downloader — async RES
Web Search & Scraping
apify-mcp-server by apify · ★11266
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website
Web Search & Scraping
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website
Web Search & Scraping
firecrawl-mcp-server by firecrawl · ★7606
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Web Search & Scraping
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Web Search & Scraping
wigolo by KnockOutEZ · ★5476
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
Web Search & Scraping
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
Web Search & Scraping
Weekly MCP digest – new and trending MCP servers in your inbox.