Web Scraping & Data Collection MCP Servers

Paperscraper

Scrape publication metadata from PubMed, arXiv, medRxiv, bioRxiv, and ChemRxiv.

Model Context

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

Alphavantage

Provides an MCP server for accessing stock market data from the Alphavantage API.

LinkedIn Profile Scraper

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

Web Research

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

Pdffigures2

Extracts figures, tables, captions, and section titles from scholarly PDFs with high accuracy.

Steel Voyager

Enables LLMs to navigate the web through Puppeteer-based tools and Steel, facilitating automated web interactions.

Cybersecurity News

Retrieves the latest cybersecurity news from various websites for integration with Claude Desktop.

BuiltWith

Identifies the technology stack behind any website, enabling AI assistants to provide detailed information about frameworks, analytics tools, and hosting services.

UseScraper

Extracts content from web pages using the UseScraper API.

Browser Scrape

Automates browser actions and scrapes web content using an AI-powered agent.

Perplexity

Enables web searches using the Perplexity AI API.

Airbnb Search

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

Firecrawl

Scrapes websites and extracts structured data using Firecrawl's APIs.

Puppeteer

Automates browser interactions, enabling LLMs to interact with web pages, capture screenshots, and execute JavaScript.

Decisions

Retrieves Czech court decisions and assesses act proposals for use with LLMs.

Model Context Protocol Servers

Provides a collection of specialized Model Context Protocol (MCP) servers for diverse use cases.

Cimri Investigate

Performs price research on Cimri using Puppeteer within a Model Context Protocol (MCP) example.

Raccoon AI

Leverages the LAM API for web browsing, data extraction, and complex web tasks automation.

ARES

Fetches information about Czech companies from company, beneficial owner, and insolvency registers.