Web Scraping & Data Collection MCP 서버

web scraping & data collection를 위한 엄선된 MCP 서버 컬렉션을 찾아보세요. 1069개의 서버를 탐색하고 필요에 맞는 완벽한 MCP를 찾아보세요.

Deep Research icon

Deep Research

242

Conducts in-depth, iterative research on any topic using AI-powered search, web scraping, and source evaluation to generate comprehensive reports.

Nodemw icon

Nodemw

240

Provides a Node.js client for interacting with the MediaWiki API and WikiData.

Airbnb icon

Airbnb

235

Searches Airbnb listings and retrieves detailed listing information.

Playwright icon

Playwright

229

Enables browser automation capabilities using Playwright for LLMs to interact with web pages.

Selenium icon

Selenium

215

Automates browser interactions through the Model Context Protocol using Selenium WebDriver.

LinkedIn Scraper icon

LinkedIn Scraper

214

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

GPT Researcher icon

GPT Researcher

212

Enables LLM applications to perform in-depth research through the MCP protocol.

12306 icon

12306

197

Provides a high-performance backend system for querying China Railway 12306 train ticket information using the Model Context Protocol (MCP).

G-Search icon

G-Search

182

Enables parallel Google searches with multiple keywords using a Playwright-powered MCP server.

PDF Reader icon

PDF Reader

180

Securely reads and extracts text, metadata, and page counts from PDF files (local or URL) for use by AI agents.

Open Web Search icon

Open Web Search

177

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

Rag Web Browser icon

Rag Web Browser

173

Enables AI agents and LLMs to interact with the web and extract information from web pages via the RAG Web Browser Actor.

Douyin icon

Douyin

170

Extracts watermark-free video links, video captions, and audio transcriptions from Douyin (TikTok) share links.

Maigret icon

Maigret

169

Facilitates open-source intelligence by collecting user account information from various public sources.

Puppeteer icon

Puppeteer

163

Automates browser interactions through Puppeteer for both new and existing Chrome instances.

MCPBench icon

MCPBench

159

Evaluates the performance of MCP servers for web search and database query tasks.

SearXNG icon

SearXNG

155

Integrates the SearXNG API to provide web search capabilities within an MCP environment.

Fetch icon

Fetch

155

Fetches URLs and YouTube video transcripts through an MCP server.

LinkedIn icon

LinkedIn

154

Enables interaction with LinkedIn's Feeds and Job API through a Model Context Protocol (MCP) server.

Paper Search icon

Paper Search

151

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

Showing 20 of 1069 results

Scroll for more results...