Web Scraping & Data Collection MCP 服务器

Web Browser

Enables AI assistants to browse websites and extract content using CSS selectors via a Minimum Control Program (MCP) interface.

Steel Voyager

Enables LLMs like Claude to interact with and automate web browsers via the Model Context Protocol.

Tavily Search

Enables search functionality via the Tavily API within Claude Desktop and other compatible environments.

Chrome Debug

Enables debugging webpages using Large Language Models by providing an MCP server for Chrome.

Pubmed Search

Searches PubMed via the Model Context Protocol (MCP).

Instagram Server Next

Fetches Instagram posts using a Chrome browser session via the Model Context Protocol.

HorizonDataWave

Provides comprehensive access to LinkedIn data and functionalities, enabling data retrieval and user account management via the HorizonDataWave API.

Weather

Retrieves current weather information for a specified city using the Open-Meteo API.

Chrome Control

Enables LLM agents to control a local Chrome browser instance programmatically via the Chrome DevTools Protocol (CDP).

Serper Search

Integrates Google search capabilities, enhanced by AI-powered deep research, into Model Context Protocol-enabled applications.

Youtube Transcript

Fetches YouTube video transcripts for integration with Large Language Models via Model Context Protocol.

Deep Research

Enables Claude and other MCP-compatible AI assistants to perform comprehensive research by integrating web and academic search functionalities.

Jina Reader

Fetches the content of a remote URL as Markdown using Jina Reader.

Puppeteer Vision

Scrapes webpages and converts them to markdown, leveraging AI to handle interactive elements automatically.

Patent

Enables access to United States Patent and Trademark Office (USPTO) data through the Patent Public Search API and the Open Data Portal (ODP) API.

Scientific Papers

Empowers Large Language Models with real-time access to scientific papers from arXiv and OpenAlex.

XHS CLI

Automate login, content publishing, search, discovery, and interaction tasks on Xiaohongshu.com.

Media Crawler

Collects public data from popular self-media platforms like Xiaohongshu, Bilibili, Douyin, Kuaishou, Weibo, Tieba, and Zhihu, integrating with AI assistants.

Paper Distill

Facilitates academic paper search, intelligent curation, and multi-platform distribution using the MCP protocol.

Labor Law

Acquires Japanese labor and social insurance laws and administrative notices from official government sources.