Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

MCP Cheat Engine Server — provides safe, structured read-only access to memory analysis and debugging functionality through the Model Context Protocol (MCP).

AI-powered content pipeline: trend discovery → research → social publishing. Built with Claude Agent SDK + MCP.

墨问笔记API的MCP服务器封装,支持在Cursor、Claude Desktop等MCP客户端中操作墨问笔记

BeeMCP: an unofficial Model Context Protocol (MCP) server that connects your Bee wearable lifelogger to AI via the Model Context Protocol

Stdio MCP Server wrapping custom Python runtime (LocalPythonExecutor) from Hugging Faces' `smolagents` framework.

A Model Context Protocol (MCP) server for interacting with Home Assistant. This server provides tools to control and monitor your Home Assistant devices through MCP-enabled applications.

An MCP server for Keycloak, designed to work with Keycloak for identity and access management, covering, Users, Realms, Clients, Roles, Groups, IDPs, Authentication.

An advanced MCP server for through a knowledge graph with capabilities. This server extends the basic memory concepts with semantic search, document processing, and hybrid retrieval for more...

A Todo List MCP Server

A Windows Event Log MCP

An Awesome MCP Server to help building mobile apps in React/Vue/Angular/VanillaJS using Capacitor and Ionic

A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
Agent Skills

CyberOwl AI Aggregates security advisories from 10 international CERTs daily and provides an AI skill that cross-references alerts against your project's tech stack. cyberowlai.

AI 驱动的短剧全流程自动化制作系统。通过 Claude Skills 实现从剧本编写、角色设计、分镜生成到视频提交的完整工作流。

An LLM programming assistant engine built with Go. It provides capabilities via the WebSocket protocol, supporting multi-turn dialogues, tool calling, permission control, and skill extension.

LightClaw: The Real Lightweight AI Assistant

Turn any LLM into a deterministic World Cup prediction engine with one prompt.

LLM Wiki 是一种用 LLM 构建个人知识库的方法论。与传统 RAG(每次查询从头检索)不同,LLM 会**,知识随每次导入和查询不断积累,形成复利效应。

一个封装了产品经理核心思维的 skill,帮助非产品经理用户写出高质量的产品需求文档(PRD)。 A skill that encodes core product management thinking to help non-PM users write high-quality Product Requirement Documents.

An agent-oriented skill for turning an SVG into a hand-drawn animation deliverable.

This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.

AI Skill tra cứu thuế TNCN, SOP kê khai/quyết toán, hướng dẫn theo nhóm đối tượng.

A comprehensive collection of Claude Skills for financial investment analysis, covering both US and China A-share markets, providing end-to-end analytical capabilities from value screening to...

This project contains two Claude Code skills: