Web Scraping & Data Collection MCPサーバー

Newsnow

28

Aggregates trending news and hot topics from multiple platforms via the Newsnow API, leveraging the Model Context Protocol (MCP).

Pdf Reader

28

Extracts text content from PDF files, supporting both local files and URLs.

WebScraping.AI

27

Extracts data from web pages using a Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI.

YouTube Transcript

26

Extracts transcripts from YouTube videos, enabling content analysis and processing.

AutoGen SSE Stdio

26

Integrates local and remote tools with AI agents using the Model Context Protocol (MCP) within the AutoGen framework.

Fetch

26

Enables fetching web content and processing images for use with Claude Desktop or other Model Context Protocol (MCP) clients.

Dumpling AI

26

Integrates with Dumpling AI to provide data scraping, content processing, knowledge management, AI agent, and code execution capabilities.

Rod

26

Automates browser interactions and provides web interaction capabilities for applications using the Rod browser automation framework.

Crawl4AI

25

Enables web scraping and crawling capabilities for Large Language Models.

Browser

25

Enables Large Language Models (LLMs) to interact with web pages through Anchor Browser's cloud-based remote browser service.

Chrome Extension Bridge

25

Enables interaction between web pages and a local server by establishing a WebSocket connection, allowing access to browser APIs and DOM elements.

Apollo.io

25

Integrates with the Apollo.io API, enabling AI assistants to enrich data, perform searches, and find job postings.

Tushare

25

Facilitates intelligent stock data analysis through a Model Context Protocol (MCP) server.

DocSearch

24

Crawls websites, generates Markdown documentation, and makes that documentation searchable.

CodingBaby Browser

23

Automates Google Chrome through AI agents via a WebSocket connection to a browser extension.

Video Digest

23

Transcribes and summarizes video content from various online platforms using multiple transcription service providers.

VibeCoding

23

Automates web search and report generation using a LangGraph-based multi-agent system.

Telegram

23

Enables AI models like Claude Desktop to interact with Telegram channels and groups for comprehensive content scraping and analysis.

JigsawStack

23

Enables AI models to interact with JigsawStack models through a Model Context Protocol server.

Gemini DeepSearch

22

Automates multi-step web research using Google Gemini models and Google Search to synthesize information and produce citation-rich answers.