Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
🚀 Intelligent MCP server bridging Claude AI with Dash (macOS documentation browser). Transforms local Dash docsets into context-aware documentation assistant with fuzzy search, project detection,...
BloodHound MCP (Model Context Protocol) is an innovative extension of the BloodHound tool, designed to enable Large Language Models (LLMs) to interact with and analyze Active Directory (AD) and Azure...
Metis is an advanced AI agent platform with an intelligent MCP (Model Context Protocol) router that dynamically manages up to 1,000+ MCP servers.
An MCP server that provides ripgrep (rg) search capabilities to any MCP client such as Claude.
This is an MCP (Model Context Protocol) server that gives Claude the ability to see and interact with any macOS application - just like Playwright does for web browsers, but for native Mac apps.
✨用Java实现的MCP，爬取最新热点新闻，允许LLM调用。告别信息茧房，用AI洞悉世界。
A Model Context Protocol (MCP) server for Minimax AI integration, providing async image generation and text-to-speech with advanced rate limiting and error handling.
A Docker-based server that gives AI agents (GitHub Copilot, Claude, etc.) direct access to a full Kali Linux penetration testing toolkit.
Claude Memory MCP Visualizer
MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation
Control UEFN (Unreal Editor for Fortnite) from Claude Code via the Model Context Protocol.
A Model Context Protocol (MCP) server that provides access to WolframAlpha's LLM API. https://products.wolframalpha.com/llm-api/documentation
Agent Skills
Built for humans, AI agents, and CI/CD pipelines.
把一句中文口播、观点或抽象概念，制作成适合知识讲解视频的“纸上钢笔线稿 + 选择性彩铅填色”动画素材。
Clouds Coder Cloud CLI Coder Runtime CLI execution plane × Web user plane for reliable, observable Vibe Coding.
还在对着大学里动辄上百页、逻辑乱得像毛线团的课件欲哭无泪？别慌，你不是一个人在“渡劫”——现在的大学课件，仿佛统一解锁了“防自学”buff：重点藏在犄角旮旯，废话多的不知所云，明明一页能说清的知识点，偏要拆成十页凑篇幅，主打一个“让你逐页啃、熬秃头，就是不让你轻松get到核心”，对考前临时抱佛脚、想高效速成的同学，简直是折磨。
AlphaSift is an agent-friendly stock discovery and ranking engine. It scans a broad market universe, applies auditable YAML strategies, enriches candidates with optional market context, ranks them...
创建可靠的 Skill 不只是总结资料。系统需要发现任务描述中遗漏的条件， 从公开来源中提取可执行步骤，并判断每条经验可以复用到多大的范围。
IEEE Transactions on Robotics (T-RO) , 2026
_**_ Every session is a replayable trail you can run as a test.
NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill.
An autonomous white-hat security auditor. Security automation for target prep, audit, exploit construction, and execution proof.
A universal command-line tool for managing iOS and Android devices, simulators, emulators and apps from Mobile Next.
Agent skills for secure smart contract development with OpenZeppelin Contracts libraries.