Web Scraping & Data Collection Servidores MCP

Web Retrieval

Analyzes web page design structures and extracts detailed information about layout, navigation, content, forms, and other elements.

Finance

Integrates with SEC EDGAR to provide comprehensive financial data and analysis tools for Large Language Models.

AI Surge

Gathers and processes premier global AI information for integration into LLM conversations.

AER

Searches for papers from the American Economic Association (AEA) using Large Language Models (LLMs).

GovInfo

Provides LLM-friendly access to the official GovInfo API v4 for searching and retrieving U.S. government documents.

Document Parser

Parse various document formats like PDF, Word, Excel, and PowerPoint to extract their content.

Prozorro

Enables AI models to seamlessly access Ukrainian government procurement data from the Prozorro public procurement system.

Websets

Integrates Exa's Websets API with MCP-compatible clients like Claude Desktop, Cursor, and Windsurf to manage dynamic collections of web entities.

Edgar Sec

Retrieves and analyzes SEC filings for data extraction.

YouTube Subtitles

Enables AI assistants to download and analyze YouTube video subtitles.

Korea Weather

Retrieves weather forecast information for locations in South Korea using the Korea Meteorological Administration APIs.

Playwright Lighthouse

Analyzes web site performance and captures screenshots using Playwright and Lighthouse.

Media Downloader

Download videos and audio from various internet sources, with support for agentic server operations.

Website Downloader

Downloads websites and their assets for use with Retrieval-Augmented Generation (RAG) systems.

LCBro

Orchestrates browser automation tasks with Playwright and Chrome DevTools Protocol, incorporating intelligent preprocessing and LLM-driven data cleaning.

Usensedata China Company Query

Provides an MCP-compatible server with tools to query comprehensive Chinese company data, enabling seamless integration with large language models.

AnyCrawl

Provides advanced web scraping, crawling, and search capabilities, integrating with large language model clients via the Model Context Protocol.

Tomba

Integrates with the Tomba.io API to provide comprehensive email discovery, verification, and enrichment services through a standardized Model Context Protocol (MCP) interface.

Youtube Transcripts

Extracts transcripts from YouTube videos via the command line.

Research Orchestration Service

Orchestrates research tasks by gathering, analyzing, and synthesizing information from multiple sources using AI to answer complex queries.