Web Scraping & Data Collection MCP Servers

Whois

Performs comprehensive WHOIS domain lookups by directly querying authoritative servers for detailed registration information across numerous TLDs.

Temporary

Integrates Discord API, executes Python code in persistent IPython sessions, and extracts URL content with readability parsing.

Woolworths

Automates interactions with Woolworths Australia's online shopping platform, enabling product browsing, cart management, and special offer retrieval.

Simple Google Search

Enables Google searches and webpage content extraction via the Model Context Protocol.

Screenshot

Facilitates agents in capturing website screenshots through a dedicated server.

Web

Facilitates DuckDuckGo web searches and content fetching for AI agents, requiring human intervention for CAPTCHA challenges.

Food

Provides comprehensive search for food products, including pricing and nutritional data, for AI agents.

Fetch Weather

Provides current city weather data through a minimalist Model Context Protocol (MCP) server, serving as an example for LLM-tool communication.

Firecrawl

Integrate powerful web scraping and crawling capabilities into large language model clients for enhanced context and data retrieval.

Dad Jokes

Provides a lightweight Model Context Protocol server to retrieve, search, and identify dad jokes from icanhazdadjoke.com.

Exa

Enables AI assistants to perform real-time web searches and access specialized data using the Exa AI Search API.

Twitter Spaces Downloader

Automates the download and AI-powered transcription of Twitter Spaces.

Browserbase

Enables large language models to automate web browsers for various online interactions and data collection tasks.

Sonata

Orchestrates browser automation for government services, transforming bureaucratic web interfaces into programmable APIs for LLM agents.

Beatport Scraper

Extracts comprehensive track metadata, audio preview URLs, and cover artwork from Beatport track URLs.

Tavily

Empowers AI systems to access real-time web information and perform advanced data extraction, mapping, and crawling.

Hello Server

Provides a foundational template for building and deploying custom MCP servers using the Smithery framework.

IPMA

Provides natural language access to meteorological and seismic data from the Portuguese Institute for Sea and Atmosphere (IPMA).

Document Extractor

Extracts and stores documentation from Microsoft Learn and GitHub URLs into PocketBase, enabling powerful search and retrieval for AI agents.

DocsScraper

Provides semantic search capabilities over documentation chunks using embeddings and AI validation, connecting to a web API.