Web Scraping & Data Collection MCP Servers

DuckDuckGo

Enables web searches using DuckDuckGo within Model Context Protocol (MCP) environments.

Git Repo Browser

Provides a tree-like representation of a Git repository's directory structure and reads specified file contents.

BrowserCat

Automates browser interactions via a cloud-based service for tasks like navigation, screenshot capture, and JavaScript execution.

Steam Review

Retrieves reviews and information for Steam games using the Model Context Protocol.

Web Search

Enables free web searching using Google search results without requiring API keys.

Youtube

Extracts video metadata and captions from YouTube videos, converting them to markdown with customizable templates.

Etoro Portfolio

Enables interaction with eToro's public API endpoints for fetching portfolio data and instrument details.

Youtube Transcripts

Extracts transcripts from YouTube videos via the command line.

Puppeteer

Automates browser interactions using Puppeteer to enable LLMs to interact with web pages and execute JavaScript.

TikTok

Extract insights from TikTok data through video discovery and metadata retrieval.

AI Surge

Gathers and processes premier global AI information for integration into LLM conversations.

Crypto PowerData

Acquires comprehensive cryptocurrency data and performs advanced technical analysis using the Model Context Protocol.

Google Ads Library

Provides instant answers and deep insights by connecting to Google's public Ads Transparency Center, allowing users to search, analyze, and compare advertising strategies.

Nexus

Integrates various digital services into a unified personal assistant server, managing calendars, notes, tasks, and web content.

NFL

Manages NFL data, provides comprehensive fantasy league tools, and extracts web content for AI applications via REST and FastMCP protocols.

DeepSearch

Enables AI models to leverage the Gemini 2.5 Flash Deepsearch model for powerful, internet-connected search capabilities.

Scrapfly

Empowers AI assistants with real-time access to any website for advanced web scraping and data extraction.

Document Parser

Parse various document formats like PDF, Word, Excel, and PowerPoint to extract their content.

Osascript

Execute macOS AppleScript and JavaScript for Automation (JXA) commands securely to automate system interactions.

Web Forager

Enables AI agents to search the web, news, and fetch web page content, converting it for LLM consumption.