Web Scraping & Data Collection MCPサーバー

Trafilatura

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

Bibextract

Extracts survey content and bibliography in BibTeX format directly from arXiv papers.

DuckDuckGo

Provides DuckDuckGo search capabilities and web content fetching as a Model Context Protocol (MCP) server.

Browserbase

Integrates Browserbase's headless browser capabilities with large language models (LLMs) via the Model Context Protocol (MCP).

LinkedIn Profile Scraper

Scrapes LinkedIn profile data asynchronously using the RapidAPI LinkedIn Profile Scraper API.

Cloudflare Playwright

Empowers AI assistants to perform web automation tasks by controlling a browser through a Model Control Protocol (MCP) server.

Airbnb Search

Searches Airbnb listings and retrieves detailed information, providing direct links to the listings.

Weather Data

Integrates real-time weather information with a standardized context protocol for sharing environmental data across systems.

APRS.fi

Connects to the APRS.fi API to facilitate ham radio position tracking and balloon chase operations, integrated with Claude Code for AI-powered data analysis.

Abstract API

Provides a unified server for diverse Abstract API services, offering comprehensive data validation, geolocation, timezone, and web utilities through a single API key.

ArXiv LaTeX

Processes arXiv LaTeX sources to enable precise interpretation of mathematical expressions by Large Language Models.

Browser Manager

Manages and automates web browsers, providing an interface to control browser functions, tabs, and web page interactions.

MVG Störung

Provides cached access to Munich Public Transport (MVG) disruption data.