Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform
Enable your AI agents to read, analyze, and modify Figma designs.
A Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, allowing AI assistants to build structures, explore the world, and interact with the game...
Agent-native knowledge engine — search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX.
飞书/Lark官方 OpenAPI MCP
Feishu / Lark 飞书文档与任务管理工具，支持 MCP 服务器和 CLI + Skill 两种使用方式，可无缝集成 Cursor、Claude Code、Cline 等 AI 编码工具
Cross-device clipboard sync for macOS, Windows & Linux — end-to-end encrypted, LAN-only, no cloud. OCR, CLI and MCP server built in.
Things.app MCP Server
Official SonarQube MCP Server for code quality and security in AI agents
An MCP for Godot that lets you create and edit games in the Godot game engine with tools like Claude
A MCP Server for APK Tool (Part of Android Reverse Engineering MCP Suites)
A docker MCP Server (modelcontextprotocol)
Agent Skills
Speedily search and merge log messages by datetime
这里放的是我希望 Agent 长期带着走的工作流：能触发、能执行、能验证、能复用，而非临时 prompt 或一次性脚本。
每个 Skill 是一个 Markdown 文件，被 AI 编程助手（如 Trae、Cursor、Copilot 等）加载后，能够引导 AI 正确完成嵌入式开发任务——从环境搭建、项目创建、编译、烧录到调试，全链路覆盖。
DeepAgent 기반 Research(연구) Multi Agent System 구축 - Context Engineering
Battle-tested execution playbooks that give any AI agent the exact commands, APIs, and patterns it needs — cutting token usage by and making local models as capable as GPT-4.
Describe your workflow in one sentence, and get a complete workflow definition file ready to import into Coze, Dify, or ComfyUI — including node configuration, edges, layout, and all...
【Skill】AI 电子书制作工作流 — Claude Code Skill
MiniQMT 量化交易开发技能（miniqmt-skill）是一个基于迅投 XtQuant 库的量化交易开发工具，提供行情数据获取和交易执行功能。适用于开发股票、期货、期权等量化交易策略，支持历史/实时行情数据下载、K线/分笔数据获取、财务数据查询、自动下单/撤单、持仓查询、资产查询等功能。
From prompts to systems — learn how to build reusable AI skills.
微信聊天记录skill
Nix packaging for OpenClaw-adjacent tools, with per-tool OpenClaw plugin metadata. Part of the nix-openclaw ecosystem.
Design evaluation rubrics for LLM/agent outputs: criteria, scores, failure modes, examples.