Web Scraping & Data Collection MCP 서버

NPI Registry

Enables searching the National Provider Identifier (NPI) registry via a Model Context Protocol (MCP) server for integration into LLM contexts.

Playwright

Exposes core browser automation capabilities via a simple API, enabling programmatic control of web browsers.

Article Scraper

Extracts article content, including title, text, author, and date, from web URLs.

TW Stock Agent

Offers a Model Context Protocol server for querying and analyzing Taiwan stock market data.

ScholarScope

Integrates with academic APIs to search for papers, authors, and institutions, retrieve citations, and fetch full-text articles.

Puppeteer

Provides advanced web scraping and data extraction tools via a Model Context Protocol (MCP) server, designed for seamless integration with AI agents and automation clients.

OSRS

Enables programmatic access to Old School RuneScape (OSRS) Wiki content and core game data definitions.

DeFi News

Searches and retrieves DeFi news from targeted websites, providing structured access to decentralized finance information.

HK Environment

Provides access to Hong Kong government environmental data through a FastMCP interface.

Playwright

Provides comprehensive browser automation capabilities for AI assistants using Playwright.

DeepRef

Connects large language models with scholarly APIs to retrieve and structure citations and abstracts for trustworthy research assistance.

QAnon

Provides a Model Context Protocol (MCP) server enabling AI analysis of QAnon posts for sociological research.

LangGraph Financial Agent

Integrates Model Context Protocol with LangGraph to build an intelligent ReAct agent capable of accessing real-time financial data.

MCP Tools

Provides AI-powered tools for web search, mathematical calculations, and tech news aggregation using the Machine Communication Protocol.

Kv Extractor

Extracts key-value pairs from arbitrary, noisy, or unstructured text using LLMs and provides type-safe output in JSON, YAML, or TOML formats.

Hot Topic

Fetches trending topics from various online platforms using the Model Context Protocol (MCP).

Serper

Enables LLMs to access and utilize Google Search results via the Serper API.

Dresden OpenData

Enables AI agents to automatically discover, fetch, and process open civic datasets from Dresden's OpenData Portal.

Browser Scrape

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

Crawl4AI

Establishes a connection and provides a standardized protocol for interacting with a Crawl4AI Docker API server.