Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
A Node.js-based Model Context Protocol (MCP) server for managing Proxmox VE hypervisors: nodes, QEMU VMs, and LXC containers, with configurable permission levels and Terraform/OpenTofu export.
A Model Context Protocol (MCP) server that enables AI assistants like Claude to work directly inside SAP BW/4HANA systems — reading, creating and modifying BW modeling objects via the same internal...
A simple Model Context Protocol (MCP) server for generating memes using the ImgFlip API. This server enables AI models and tools to generate meme images from user prompts.
A lightweight, handcrafted implementation of the Model Context Protocol focused on what most users actually need: exposing tools with clean Python type annotations.
Give AI agents or scripts direct control over your parametric design canvas and Rhino rendering tools.
MCP X-Ray is a unified open-source security scanning and penetration testing solution for Model Context Protocol (MCP) servers.
Remote Model Context Protocol (MCP) server for cross-platform ad management. Create, analyze, and optimize campaigns across from any MCP-compatible AI assistant.
B站（Bilibili）MCP Server —— 让 AI 助手直接操作B站。
Automate supported timeline, media, audio, effect, caption, graphics-template, and export workflows through Claude, GPT, or another Model Context Protocol client.
A Model Context Protocol (MCP) server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question.
Godot MCP bridges the gap between AI assistants and the Godot game engine by providing a standardized Model Context Protocol interface.
A Model Context Protocol (MCP) Server for Joplin that enables note access through the Model Context Protocol. Perfect for integration with AI assistants like Claude.
Agent Skills
Foundation Lab is a native iOS and macOS workbench for learning, testing, and shipping with Apple's Foundation Models framework.
简单说，就是跟 Claude 说一句话，它会帮我从每天的新论文里筛一轮，挑出值得看的，再把重点论文读完、写成 Obsidian 笔记。日常不用记一堆命令，基本就是：
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and...
Frappe UI provides a set of components and utilities for rapid UI development. Components are built using Vue 3 and Tailwind. Along with generic components like Button, Link, Dialog, etc.