Back to search
30
MCP

Scraper

pulsemcp/scraper

Extracts content from websites through four core tools for HTML scraping, markdown conversion, text extraction, and link discovery with batch processing, caching, proxy support, and CSS selector filtering for reliable web content extraction and research automation.

Uptime
0.0%
1 probes
Response
0ms
last probe
Tools
0
callable
Primary URL
—

Similar MCP servers embedding-nearest

Web Scraper
Extract clean Markdown from any URL, removing boilerplate for use in RAG pipelines.
0 tools
Web Page Content Extractor
Extract clean text, headings, links, and metadata from any web page. Returns structured data with title, description, OG tags, up to 5000 ch
0 tools · http
Web Content Extractor
Extracts and processes web content for use in AI workflows.
0 tools
URL Text Fetcher
Extracts visible text content and hyperlinks from web pages using requests and BeautifulSoup4 for web scraping, content analysis, and link d
0 tools
Website Scraper and Analyzer
Enables website analysis and content extraction using Cloudflare Workers, providing tools to scrape, summarize, and answer questions about w
0 tools
TheCrawler
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
0 tools

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "scraper": {
      "url": "None",
      "transport": "http"
    }
  }
}