Web Scraping Servers

Enables LLM-powered browser automation for web tasks including navigation, interaction, and content extraction through Playwright's comprehensive browser control capabilities.

Provides secure access to YggTorrent through an unofficial API wrapper, enabling torrent searching with category filtering, detailed metadata retrieval, and magnet link generation with automatic passkey injection for authenticated downloads.

F

Fetch and Convert

Remote

Fetches and converts web content to Markdown using JSDOM and Turndown.

Y

YouTube Transcripts

Remote

Extract and analyze video captions and subtitles in multiple languages.

Integrates YouTube subtitle retrieval for natural language queries about video content.

R

Read Website Fast

Remote

Extracts web content and converts it to clean Markdown format using Mozilla Readability for intelligent article detection, with disk-based caching, robots.txt compliance, and concurrent crawling capabilities for fast content processing workflows.

Connects to GitHub repositories, enabling natural language queries about code structure, dependencies, and development history.

Integrates with web content sources to fetch, convert, and summarize online information for real-time data retrieval and analysis.

Provides RSS feed parsing and retrieval with RSSHub integration, automatically trying multiple instances when one fails and supporting custom rsshub:// protocol URLs for accessing current content from websites, social platforms, and news sources that don't natively provide RSS feeds.

Bright Data

Official

Integrates with Bright Data's web scraping infrastructure to provide real-time access to public web data through specialized tools for search engine scraping, webpage extraction, and structured data retrieval from popular websites.

Leverages Playwright and BeautifulSoup to enable robust web scraping and content extraction, converting complex JavaScript-heavy web pages into high-quality Markdown with browser automation capabilities.

ScrAPI

Official

Enables web scraping from sites with bot detection, captchas, or geolocation restrictions through residential proxies and automated captcha solving for content extraction in HTML or Markdown formats.

WebScraping.AI

Official

Provides web scraping capabilities with proxy support, JavaScript rendering, and structured data extraction for robust web content retrieval and analysis.

Y

YouTube Transcript

Remote

Extracts and formats YouTube video transcripts with language selection, paragraph formatting, and metadata enrichment for content analysis and research workflows.

Integrates with OLX marketplaces across five European domains using web scraping to search listings with filters and retrieve detailed property information including seller data for market research and price monitoring.

Enables AI to access text content from websites protected by bot detection mechanisms through three protection levels (basic, stealth, max-stealth), retrieving complete pages or specific content patterns without manual copying.

Integrates web scraping and image processing capabilities to fetch, extract, and optimize web content.

W

Web Content Pick

Remote

Extracts structured content from web pages using customizable selectors for crawling, parsing, and analyzing HTML elements without leaving the assistant interface.

Enables AI to access and manage RSS feed content by parsing OPML files, fetching articles, and filtering content from subscribed sources

Combines Brave Search with web scraping to provide deep research capabilities by extracting full content from pages and traversing links at configurable depths

Web Reader

Official Remote

The Web Reader MCP Server is a Z.AI implementation based on the Model Context Protocol (MCP). It provides Claude Code, Cline, and other MCP-compatible clients with powerful web content extraction capabilities, including full-page content retrieval and structured data extraction.