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

Superhuman Mail MCP Server

TypeScript toolkit for the Plaud API: core library, CLI, and MCP server with automatic token management.

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dispatch, sessions, async jobs, agent dialogues.

The agent never holds a kubeconfig. Every write is policy-checked, human-approved, and traced.

Give Claude Code eyes for your frontend. No more blind debugging where Claude guesses about your UI, you take screenshots, and you go back and forth hoping it understands what's broken.

MCP server that exposes the CODESYS V3.5 IDE scripting API as 41 tools and 3 resources, with the CODESYS UI kept open across calls via a file-based IPC watcher.

Agent-operated App Store and monetization ops: metadata, IAPs, subscriptions, RevenueCat, paywalls, ASO, and analytics

blender-ai-mcp lets Claude, ChatGPT, Codex, and other MCP clients control Blender through a stable tool API instead of ad-hoc Python generation.

A minimal MCP server built on crawl4ai for LLM-friendly web extraction

A Model Control Protocol (MCP) server that allows Claude to communicate with locally running LLM models via LM Studio.

MCP server for Agentset, an open-source platform for Retrieval-Augmented Generation (RAG). Designed for developers who want to build intelligent, document-based applications quickly and efficiently.

Complete Docker-based AI operations infrastructure: Paperclip, n8n, Supabase, OpenClaw, ruflo, and MCPs
Agent Skills

Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet...

Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.

A Claude skill for designing comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing).

Autonomous skill generator that enables AI agents to learn new technologies from the web. Use this skill when you want to research a library, framework, or tool and generate reusable...

回忆的意义不只在于回忆,更重要的是从中复盘经验教训,成为更好的自己。本项目基于 therealXiaomanChu/ex-skill 开发

Distills Linus Torvalds' code-review methodology from his LKML emails into a reusable, language-agnostic skill.

微信读书前几天上了一个官方 AI skill(weread.qq.com/r/weread-skills),把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强,但它只是「自然语言包装的搜索接口」——你让它推荐书,它不会去看你已经读过什么,常把你笔记 68 条的书又当新书推回来给你。

AI-powered business research capabilities through MCP protocol. Enables multi-agent research workflows for consumer insights, product R&D, market analysis, and automated report generation.

代码道场:让 AI 陪你从看不懂项目到能独立魔改 · AI-powered learning workflow for real code projects

Lightweight and Memory efficient terminal for Mac built with SwiftUI and libghostty . Mac | iOS | Android | Discord

, verb. To stamp a mark that cannot be erased. noun. The mark itself, permanent, portable, unmistakably yours.

agentchengfeng/writing-assistant-skill agent skill.