Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
An Awesome MCP Server to help building mobile apps in React/Vue/Angular/VanillaJS using Capacitor and Ionic
A Windows Event Log MCP
A Todo List MCP Server
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...
An MCP server for Keycloak, designed to work with Keycloak for identity and access management, covering, Users, Realms, Clients, Roles, Groups, IDPs, Authentication.
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.
Stdio MCP Server wrapping custom Python runtime (LocalPythonExecutor) from Hugging Faces' `smolagents` framework.
BeeMCP: an unofficial Model Context Protocol (MCP) server that connects your Bee wearable lifelogger to AI via the Model Context Protocol
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
AI-powered content pipeline: trend discovery → research → social publishing. Built with Claude Agent SDK + MCP.
MCP Cheat Engine Server — provides safe, structured read-only access to memory analysis and debugging functionality through the Model Context Protocol (MCP).
Agent Skills
一个面向社会科学论文写作的 Codex / ChatGPT Skill，用于辅助完成选题诊断、研究问题细化、论文大纲搭建、文献综述规划、文献检索到 Zotero 工作流、草稿评审、章节修订、引用与证据风险检查，以及投稿前检查。
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
Autonomous formalization of research-level mathematics in Lean 4
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
This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.
Heads up: the more agents you run, the more this skill is doing on hard mode — rebuilding context from transcripts every time.
— 基于 Claude Code Agent Teams 的多智能体协作安全分析框架
A community collection of skills for Minis — reusable instruction sets that extend Claude's capabilities with specialized workflows, domain knowledge, and bundled resources.
本项目是一个 Claude Code 插件，通过 SubAgents 和 Skills 实现：
OpenCode, Claude Code, Cursor, OpenClaw and beyond. Search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. All self-hosted, free, unlimited.
A portable skill for Claude Code, Codex, Antigravity — or any AI agent — that turns long-form Markdown (plans, specs, system designs, RFCs, runbooks, postmortems, brainstorms, notes) into a single...