Web Scraping & Data Collection MCPサーバー

SearXNG Integration

Enables privacy-focused meta-search capabilities by integrating with SearXNG.

Hong Kong Misc

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

Ytrnscrpt

Enables Claude to fetch and analyze YouTube video transcripts.

Isparta University OBS

Integrates with Isparta University's Student Information System to securely access and manage academic data.

PDFFigures

Extracts figures and tables from PDF documents through an HTTP interface powered by PDFFigures 2.0.

Model Context Examples

Offers a collection of example server implementations for Model Context Protocol development, featuring real-time weather alerts and web search integration.

VideoSum

Extracts content from multiple video platforms and generates intelligent knowledge graphs with OCR support.

DuckDuckGo Search

Enables intelligent search tasks by integrating the DuckDuckGo MCP Server with a LangChain Groq LLM agent.

Gedcom

Manages and enriches genealogical data, enabling AI agents to create, edit, and query GEDCOM files.

Crawl4AI

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

PDF Reader

Provides server-based capabilities for extracting text, recognizing OCR content, and extracting images from PDF documents.

Xiaohongshu Automation

Automate core interactions with Xiaohongshu, including login, content publishing, searching, commenting, and user profile retrieval, via standardized interfaces for AI Agents.

Browser Scrape

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

Fayeblade

Facilitates browser automation by providing a robust bridge that communicates over `stdin/stdout` using a JSON-RPC-like protocol.

YouTube

Fetches and extracts transcripts from YouTube videos, enabling AI/LLMs to process video content.

NPI Registry

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

Terminal Control

Enables AI agents and programs to interact with terminal applications through a virtual X11 display.

Mineru

Converts PDF documents to HTML, including image resource organization and renaming, by encapsulating Mineru's official parsing capabilities as a FastMCP service callable by any MCP-compatible client.

Scraper Engine

Provides a basic server for web scraping tasks.

YouTube Knowledge

Transforms YouTube into a queryable knowledge source, powering AI workflows and detailed content analysis.