Web Scraping & Data Collection MCP 服务器

Ytrnscrpt

Enables Claude to fetch and analyze YouTube video transcripts.

Web Content Pick

Extract structured content from web pages using customizable selectors and crawling options.

Patent Integration

Configures a server for integrating patent data from multiple API sources.

HK Food

Provides access to government food-related data in Hong Kong through a FastMCP interface.

Jina AI

Converts web pages into Markdown format, optimized for large language models.

Librarian

Enables large language models to query Wikipedia for information and automatically fact-check factual claims.

Context

Provides intelligent context management and web content fetching capabilities for AI assistants.

Rec

Locates camping facilities and recreational areas leveraging Recreation.gov's RIDB API and Google Maps Geocoding API.

Web Scraper

Crawl and extract content from dynamic websites using a server-based approach.

Bright Data

Enables Large Language Models and AI agents to access, search, and navigate the web in real-time without encountering blocks.

WebScout

Automates the reverse engineering of web applications and streaming APIs to discover, analyze, and capture network traffic.

Hacker News

Access and integrate Hacker News data programmatically, offering tools to retrieve stories, search, and manage content.

SpaceX

Serves dynamic SpaceX API data over the Model Context Protocol.

Zget

Archive videos from hundreds of online platforms into a personal, self-hosted library with comprehensive search and metadata preservation.

LinkedIn Sales Navigator

Automates lead generation, profile research, and outreach workflows on LinkedIn Sales Navigator through AI assistants.

MEGA Account Generator

Generates MEGA.nz cloud storage accounts programmatically via a minimal JSON-over-stdio server.

Image Tiler

Tiles large images and screenshots to prevent LLM vision downscaling, ensuring every detail is visible to models like Claude, GPT-4o, and Gemini.

Awesome Fetch

Provides a secure, high-speed URL fetching and content extraction service for large language model agents.

Visus

Pre-filter and sanitize web content for LLMs, removing noise, redacting PII, and detecting prompt injection attempts.

Google News

Provides AI assistants with real-time Google News RSS feeds, featuring automatic URL decoding, concurrent processing, and intelligent caching.