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

MCP server for YouTube — search videos, channels, playlists, and transcripts. Works with Claude, Cursor, Windsurf, and any MCP client.

MCP server for searching and reading books from your Calibre ebook library

A Model Context Protocol (MCP) server implementation exposes document processing capabilities through natural language, supporting both direct human interaction and AI agent tool calling.

A catalog of single-file MCP servers for .NET 10

A blazing-fast MCP (Model Context Protocol) server for multi-engine web search, written in Rust.

A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.

ČSFD API in JavaScript. Amazing NPM library for scrapping csfd.cz. Now with MCP server

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.
Agent Skills

xiaohongshu-skills

One-command tmux setup with terminal automation for AI agents.

把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)

A curated collection of open-source macOS applications built with Swift

Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.

Prismer Cloud

Agent skills for useful HTML artifacts, wireframes, interactive prototypes, plans, and diagrams.

extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero human intervention.

My profile & the agent skills I created

ShinkaEvolve : Towards Open-Ended and Sample-Efficient Program Evolution 🧬

A passive recording project allows you to have complete control over your data. Automatically take screenshots of all your screens, index them, and save them locally.