Web Scraping & Data Collection MCP 服务器

CTFtime

Provides programmatic access to CTFtime.org data, enabling retrieval of CTF competition details, team rankings, and event results through a standardized interface.

Browser

Enables AI assistants to control a web browser through a WebSocket-based Model Context Protocol server.

Web Analyzer

Performs high-performance web analysis, content summarization, and structured data extraction for diverse applications.

YouTube Ultimate Toolkit

Empower Claude AI with comprehensive access to YouTube content, including transcripts, metadata, comments, screenshots, and audio clips.

AI Local Agents

Build autonomous AI agents for local LLM inference, memory handling, and voice interaction, automating various tasks without relying on external APIs.

Wuwa

Provides detailed character, artifact, and profile information for the game Wuthering Waves, formatted for large language models.

Worklog

Automates the generation and management of daily worklogs, including content collection from various AI tool sessions.

Firecrawl

Integrates advanced web scraping, crawling, and data extraction capabilities into LLM clients such as Cursor, Claude, and Windsurf.

Jmcomic AI

Integrates JMComic's core functionalities with AI agents, enabling natural language control for comic search and download.

TradingView

Fetches TradingView chart snapshots efficiently using Playwright for browser automation, enabling fast and secure visualization of market data.

Fetch

Fetches web content for Large Language Models, bypassing robots.txt restrictions.

Web Scraper Toolkit

Converts websites into LLM-ready assets like Markdown, JSON, and PDF, featuring robust anti-bot evasion and an AI-first design for agent integration.

USGS Water

Retrieve real-time water data including stream flow, gage height, and temperature from USGS monitoring stations.

Terminal Control

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

Polarsteps

Enables AI models to interact with the Polarsteps API for fetching travel data, trip information, and user profiles.

Brightspace

Connects Purdue students' Brightspace accounts to access academic data via web scraping, handling Duo Mobile 2FA.

Paper Search

Search and download academic papers from multiple sources, including arXiv, PubMed, bioRxiv, and Semantic Scholar, designed for integration with large language models.

TimeLooker

Monitors search queries, detects new content using AI, and automates payments for task creation through x402 integration.

PDF Reader

Extracts text content from PDF files, supporting both local files and URLs.

Headstarter

Provides AI assistants with access to a database of LinkedIn profiles from the Headstarter community for intelligent querying and analysis.