Web Scraping & Data Collection MCP 服务器

Tavily

Enables real-time web search, intelligent data extraction, structured website mapping, and systematic web crawling through Tavily's suite of tools, supporting both SSE and STDIO transport protocols.

Search It

Integrates simple search and web crawling functionalities accessible via an MCP Server.

Mesh

Provides AI assistants native understanding and utilization of Mesh Design System components and design tokens.

VGL CV Data

Provides programmatic access to Valentin Gonzalez Loureiro's curriculum vitae data through a Model Context Protocol server.

Multi-Search

Provides comprehensive Google search functionality through a plugin-based architecture, leveraging external APIs like Serper and SerpApi.

RateMyProfessors

Integrates with RateMyProfessors.com to fetch professor ratings, reviews, and comments via an MCP client.

YST Daily Report Collector

Automates the collection of daily KPI reports from a specified internal system, generating structured Markdown reports for a given date range.

TechCyclopedia

Provides an intelligent data pipeline for high-fidelity crawling and extraction of technical documentation, optimized for AI agents.

Research

Enables large language models to fetch, analyze, and summarize academic research papers from multiple trusted sources in real-time.

IPMA Weather

Access comprehensive Portuguese weather, sea state, fire risk, and seismic data from the IPMA API through a Model Context Protocol server.

YouTube Subtitle

Fetches YouTube video subtitles and transcripts, converting them into multiple formats including SRT, VTT, TXT, and JSON.

Specialized AI Search

Empowers AI agents with specialized search capabilities across diverse online platforms and data formats, utilizing the Model Context Protocol.

Open Webtools

Provides web search, website reading, and YouTube transcript tools for LLM clients, requiring zero API keys.

US Census

Provides AI agents with direct access to over 1,700 US Census Bureau datasets, including population, income, and demographics.

Xiaohongshu

Automate interactions with Xiaohongshu to search for notes, retrieve details, and publish new content.

TGC Screen

Controls The Golf Club 2019 simulator through screen capture, OCR, and keyboard input, bridging WSL and Windows for enhanced interaction.

MerchGent

Empowers AI agents to scrape, audit, and analyze e-commerce storefronts, providing comprehensive merchandising insights and facilitating expert analysis.

Data Center Siting Intelligence

Provides comprehensive intelligence for data center site selection, leveraging multiple government data sources to assess location viability.

AI Training Data Quality

Assess AI training data quality, detect bias, and score governance for any MCP-compatible AI agent.

Academic Commercialization Pipeline

Provides AI agents with comprehensive academic commercialization intelligence by orchestrating 8 academic and patent data sources to deliver actionable probability scores.