Web Scraping & Data Collection MCP Servers

NIH RePORTER

Enables conversational searching of NIH-funded research projects and publications via the NIH RePORTER API.

Webscan

Analyzes web content, extracts information, and identifies potential issues.

Price Monitor

Monitors product prices from Gmarket, comparing them to a database baseline and sending Slack alerts upon price drops.

Playwright

Automates browser interactions using Playwright to enable LLMs to interact with web pages.

Tripmatch

Query flight and train information using the Variflight API.

Kagi

Integrates Kagi Search and Summarizer APIs into an MCP server, offering a stable alternative for AI applications.

Search

Provides a Node.js-based Model Context Protocol (MCP) server for robust web search and intelligent content analysis capabilities.

RuneScape Wiki

Accesses RuneScape Wiki APIs to provide real-time Grand Exchange prices, item data, and player statistics for RuneScape 3.

YouTube Comments

Retrieves and expands YouTube video comments and their replies using the YouTube Data API v3, delivering the data as a structured JSON string.

Agentic Search Example

Enables AI agents to search and retrieve content from websites.

Weather

Integrates with Open-Meteo to provide current weather conditions and hourly forecasts via a Model Context Protocol server.

MyZ Search

Provides programmatic access to web search results and page content extraction via an HTTP API.

Stock Price

Provides real-time stock price information and market states from global exchanges using the Yahoo Finance API.

Hyperbrowser

Automate web browsing, scrape content, extract structured data, and crawl webpages using advanced browser agents.

Serper

Exposes the comprehensive Serper Google Search API, including its webpage scrape functionality, as an MCP server.

YouTube Captions

Fetches YouTube transcripts and subtitles using yt-dlp, providing paginated responses for integration with MCP hosts.

PageBolt

Enables AI agents to capture web content by taking screenshots, generating PDFs, creating OG images, and running browser automation directly from chat.

World Bank UNICEF Data

Integrates global economic indicators from the World Bank with child welfare metrics from UNICEF into a comprehensive dataset.

Wildberries

Retrieves and analyzes Wildberries product reviews for seamless integration with Large Language Models.

InfoMesh

Provides a fully decentralized, P2P, and free web search engine specifically designed for Large Language Models (LLMs) without the need for API keys or billing.