Web Scraping & Data Collection MCP Servers

Yt-Dlp

219

Downloads video and audio content from various online platforms for use with Large Language Models.

Playwright

256

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

Maigret

227

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

Trends Hub

222

Aggregates trending topics from across the web using the Model Context Protocol (MCP).

Google Scholar

235

Enables AI assistants to search and access Google Scholar papers through a simple interface.

Youtube Transcript

314

Retrieves transcripts for YouTube videos given a URL and desired language.

Google Search

220

Enables AI models to perform Google searches and analyze webpage content programmatically through an MCP interface.

Web Research

293

Enables Claude to access real-time information from the web for enhanced research capabilities.

Deep Research

311

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

Omnisearch

272

Provides unified access to multiple search engines, AI tools, and content processing services.

GPT Researcher

323

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

G-Search

251

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

SEC Edgar

214

Connects AI models to SEC EDGAR filings through an open-source MCP server, enabling financial research and insights.

Yahoo Finance

224

Provides comprehensive financial data from Yahoo Finance via the Model Context Protocol.

Nodemw

245

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

MCPBench

241

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

Seo

220

Retrieves SEO data from Ahrefs, providing tools for backlink analysis, keyword research, and traffic estimation.

PDF Reader

303

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

12306

283

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

Weixin Reader

266

Enables large language models to read WeChat official account articles by simulating a browser to bypass anti-scraping mechanisms.