Web Scraping & Data Collection MCP 서버

Bright Data

1,431

Empowers AI agents to access, discover, and extract real-time web data, bypassing restrictions and bot detection.

Deepwiki

1,043

Fetches and converts Deepwiki content to Markdown for use in code editors and other MCP-compatible clients.

Fetcher

883

Fetches web page content using a Playwright headless browser, enabling JavaScript execution and intelligent content extraction.

RedNote

870

Access content from the RedNote (XiaoHongShu) platform via an MCP server.

Tavily

818

Integrates Tavily's search and data extraction capabilities with AI assistants via the Model Context Protocol.

Financial Datasets

654

Provides access to real-time and historical stock market data for AI assistants through the Model Context Protocol (MCP).

Hyperbrowser

623

Scrape webpages, extract structured data, and crawl websites while providing access to browser agents.

Fetch

620

Fetches and transforms web content into various formats.

Annas

561

Facilitates searching and downloading documents from Anna's Archive as an MCP server or command-line interface tool.

Yargi

534

Facilitates access to various Turkish legal databases, providing a standardized Model Context Protocol (MCP) interface.

DuckDuckGo Search

530

Provides web search capabilities through DuckDuckGo, along with content fetching and parsing features.

Web Agent Protocol

478

Enables seamless interaction between users, web agents, and browsers by recording and replaying browser actions.

LinkedIn Scraper

458

Enables interaction with LinkedIn through AI assistants, allowing users to scrape profiles, companies, and jobs.

YouTube

456

Downloads YouTube subtitles using yt-dlp and connects to claude.ai via Model Context Protocol.

Google Search

454

Bypasses search engine anti-scraping mechanisms to execute Google searches and extract results.

Apify

449

Connects AI agents to thousands of web scraping, data extraction, and automation tools available on the Apify Store.

A-Share

435

Provides access to A-share market data through the Model Context Protocol (MCP).

Paper Search

383

Searches and downloads academic papers from multiple sources like arXiv, PubMed, and bioRxiv.

Open Web Search

376

Enables web search across multiple engines without requiring API keys, supporting Bing, Baidu, DuckDuckGo, Brave, Exa, and CSDN.

Graphlit

365

Enables integration between Model Context Protocol (MCP) clients and the Graphlit service for content ingestion and knowledge retrieval.