Web Scraping & Data Collection MCP Servers

Simple OSINT Recon

Provides a suite of Open Source Intelligence (OSINT) reconnaissance capabilities, including port scanning, username tracking, and Wigle database lookups.

Paperscraper

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

Haloscan

Provides a Model Context Protocol (MCP) server to access and utilize the Haloscan SEO API for comprehensive SEO analysis and data retrieval.

Kagi

Integrates Kagi's powerful search, summarization, and AI assistant capabilities into external applications via a Node.js server.

Puch AI WhatsApp

Connects Puch AI with WhatsApp and other services to enable automated tasks, web content fetching, and product searches.

Web Tools

Provides web search and intelligent research capabilities through Claude CLI integration for MCP clients.

Fetch

Fetches URLs and YouTube video transcripts.

Fetch

Retrieves web page content and YouTube video transcripts efficiently.

Selenium Python

Enables large language models or external tools to interact with a browser through a standardized Model Context Protocol for automation.

Perplexity

Enables AI assistants to access and utilize the Perplexity API for search and information retrieval.

TryKitt.ai

Enables AI assistants to find and verify B2B email addresses using the TryKitt.ai API.

Fetch

Fetches URLs and YouTube video transcripts through a dedicated server.

Brave Search

Integrates the Brave Search API to provide web and local search capabilities.

Scrapy

Scrapes websites, from basic HTTP requests to dynamic sites requiring JavaScript execution, using TypeScript.

SearxNG Search

Enables web searches using a SearxNG instance via the Model Context Protocol.

DNSDumpster

Enables AI assistants to perform DNS reconnaissance through natural language requests using the DNSDumpster API.

Pearch.ai

Facilitates people searches through the Pearch.ai API as a FastMCP service.

Scholar

Searches and retrieves academic papers from major databases like arXiv and DBLP, providing detailed information and PDF download links.

Domain Checker

Verify domain availability using WHOIS lookups and DNS resolution, deployable as a remote MCP server.

Google Search

Enables AI clients to perform advanced Google Custom Searches, extract web content, and conduct specialized research.