Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
An MCP (Model Context Protocol) server for Tailscale, enabling detailed queries and operations for devices, DNS, users, invites, keys, webhooks, services, logging, policy validation, and tailnet...
This is a Model Context Protocol (MCP) server that converts Figma designs to React components. It provides tools for fetching Figma designs and generating React components with TypeScript and...
mcp4k is a compiler-driven framework for building both clients and servers using the Model Context Protocol (MCP) in Kotlin.
Omnigentx Jarvis — voice + chat AI assistant powered by Fast Agent (MCP) with Vue dashboard. Single-user, self-hosted, multi-skill orchestration.
阿里云 MCP Server 是一个强大的云服务集成平台，通过 Model Context Protocol (MCP) 为 AI 应用提供阿里云服务的无缝集成能力。该平台支持数万个阿里云 OpenAPI，让开发者能够轻松地将阿里云的各种服务能力集成到 AI 工作流中。
Draw.io Model Context Protocol (MCP) Browser Extension
Stardust is a desktop AI agent platform that combines a powerful chat interface with an extensible plugin system.
。在一个桌面应用中同时管理多个 AI 会话，提供结构化对话视图、看板式任务管理、实时状态监控、Agent 编排、工作流自动化和远程控制。
The open-source control plane for Codex projects: visible progress, resumable context, safe handoffs, and reusable knowledge.
Levante is a cross-platform desktop app (Windows, macOS, Linux) that brings powerful AI tools closer to everyone — not just technical users.
Ollama MCP is a tool for connecting Ollama-based language models with external tools and services using the Model Context Protocol (MCP).
Docs • Quickstart • API Reference • Discord
Agent Skills
speaker is a Codex skill project for academic presentations. It reads a real .pptx, combines text extraction, PPTX structure inspection, slide rendering, OCR, and vision review, then generates...
photo-revival 是一个 Codex Skill。它不是给照片套滤镜，而是把照片当成“记忆证据”：保留主体、空间关系和情绪，再用新的手绘插画语言重新生成。
- We open-sourced Skiller — an automated tool that turns conversation logs or plain-text requirements into standards-compliant skill packages.
"The only rules you have to follow are the laws of physics — everything else is a recommendation."
A collection of AI agent skills focused on brand building services. Built for brand strategists, agency owners, and founders who want AI coding agents to help with brand strategy, naming, identity,...
一个**:自动转录 → AI 识别口误/口癖/静音 → 网页波形审核 → 导出 FCPXML,拖进剪映或 Final Cut Pro 完成最后一刀。核心是一份 SKILL.md,,不绑定特定工具。 这个项目灵感最初来源于GitHub开源项目 videocut-skills，为了适配我自己的剪辑工作流，重写和扩展了工程导出、前端交互、视频预览、核心剪辑逻辑、语音识别和音频识别字幕等功能
This repository contains the source code, examples, and project implementations for the book — a practical, code-first guide to building AI agents and, more importantly, putting them into production.
Open-source agent skills for generating editorial-style information cards from natural-language input.
给 Agent 一条 URL，直接拿到正文、图片和元数据；不启动浏览器，不把整页 DOM 塞进上下文。 English · 简体中文
and we're building it in the open with the community. APIs will still evolve as your feedback shapes them, so we don't recommend it for production workloads yet.
Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images
If you have used android/skills, you already know the shape of an Agent Skill: a Markdown file an agent loads on demand to perform one focused task. That library covers Android development at large.