Web Scraping & Data Collection MCP 서버

Earch

Integrates Brave Search and Local APIs into MCP-compatible clients for prompt-driven information retrieval.

RappelConso

Retrieves and exposes data from the data.gouv.fr RappelConso platform as an API.

Content Analyzer

Automates web content scraping, document processing, screenshot analysis, and local Excel database management for intelligent content workflows within Claude.

BusTimes

Provides real-time bus departure information for UK stops by scraping data from bustimes.org.

Web Search

Enables AI systems to access real-time web search capabilities.

PubMed

Exposes the PubMed E-Utilities search workflow over HTTP, providing a unified endpoint for querying medical literature and returning curated article metadata.

Model Context

Enables querying real-time weather information and accessing internet usage data using the Model Context Protocol.

Naver Flight

Retrieves the top 10 cheapest direct flight information for specific routes and dates using the Naver flight search API.

DDGS

Provides a Model Context Protocol (MCP) server for performing DuckDuckGo searches.

Ephor Youtube

Integrates YouTube functionality into Large Language Models (LLMs) via the Model Context Protocol (MCP).

YouTube Transcript

Access and retrieve YouTube video transcripts, including both manually created and auto-generated content, with secure Google OAuth 2.0 authentication.

Fetch

Enables LLMs to retrieve and process web page content, converting HTML into markdown for easier consumption.

Binance Data Tools

Provides a server to fetch real-time and historical Binance cryptocurrency data including OHLCV, mark prices, funding rates, and open interest.

DNSDumpster

Enables AI assistants to perform detailed DNS reconnaissance by querying the DNSDumpster API.

SearXNG Claude

Provides AI assistants with privacy-focused web search capabilities and URL content extraction, powered by SearXNG and built with the Model Context Protocol.

DuckDuckGo

Integrates DuckDuckGo search, analysis prompts, and region resources into Model Context Protocol (MCP) clients and provides a dedicated command-line interface.

Web Research

Empowers Claude to access and process real-time web information for comprehensive research.

Trafilatura

Extracts main content and metadata from web pages using the Trafilatura library via a Model Context Protocol interface.

Gemini URL Context & Search

Enables web page text and image extraction and Google Search capabilities for AI models via an MCP server, leveraging Google AI Studio's URL context.

Playwright

Provides browser automation capabilities to large language models by leveraging Playwright's accessibility tree for web interaction.