Web Scraping & Data Collection MCP Servers

Marginalia

Accesses the Marginalia Search engine, focusing on independent and non-commercial web content.

Sonata

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

Jason's Servers

Sets up and configures a collection of Model Context Protocol (MCP) servers for various tasks.

Perplexity

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

Playwright

Enables LLM-powered clients to control a browser for automation tasks via the Model Context Protocol.

MVG Störung

Provides cached access to Munich Public Transport (MVG) disruption data.

Webtools

Provides web analysis tools, including HTML extraction, markdown conversion, screenshot capture, performance analysis, and Lighthouse audits.

Research Server

Searches, extracts, and locally stores information about research papers from arXiv.

Chef Agent

Leverages a Neo4j-backed knowledge graph and AI agents to provide real-time recipe querying, web scraping, dynamic graph updates, and personalized cooking assistance.

CleanWeb

Extracts and cleans core web content, filtering ads and converting it into a pristine Markdown format.

CGV Cinema API

Provides a Python client for interacting with the CGV Cinema mobile API to access movie listings, locations, schedules, and seat maps.

Job Search Node

Scrapes LinkedIn job listings, performs AI-driven analysis against a candidate profile, persistently indexes relevant jobs, and offers an API for management and retrieval.

StockScreener

Analyzes stock data locally using a language model and web scraping.

Query Blogger

Access your Blogger blog content securely and efficiently, enabling large language models to retrieve blog information and latest posts.

Youtube Transcript

Retrieves transcripts from YouTube videos using the Model Context Protocol.

Master Puppeteer

Orchestrates advanced browser automation tasks using Puppeteer, providing token-efficient and comprehensive web data for AI agents.

Web Reader

Enables large language models to effortlessly retrieve and parse web content, converting it into clean Markdown format.

Perplexity

Enables web searches using the Perplexity AI API.

Google Search & Webpage Reader

Provides web search capabilities via Google Custom Search API and extracts content from any webpage.

Scrappey

Control a browser through an LLM using Scrappey's web automation and scraping capabilities.