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

Model Context Protocol server for Cyclops

CAD MCP Server

A Model Context Protocol server for Zendesk.

https://github.com/user-attachments/assets/ab1b7e63-b6f0-4d5b-85ab-79d328de31db

A Model Context Protocol server that allows you to download subtitles from YouTube and connect them to a LLM.

This Model Context Protocol server implementation of Asana allows you to talk to Asana API from MCP Client such as Anthropic's Claude Desktop Application, and many more.

Drive KiCad schematic, PCB, DRC/ERC, DFM, and manufacturing review from any MCP-capable AI agent.

MCP (Model Context Protocol) is an open protocol introduced by Anthropic that standardizes how large language models communicate with external tools, resources or remote services.

A macOS AppleScript MCP server

A Model Context Protocol server for Azure AI Foundry, providing a unified set of tools for models, knowledge, evaluation, and more.

A Model Context Protocol (MCP) server that enables Claude Desktop to search your content using Azure AI services.

A Model Context Protocol (MCP) server that provides fine-grained control over a Chrome browser instance through the Chrome DevTools Protocol (CDP).
Agent Skills

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

📱 A strongly-typed, caching GraphQL client for iOS, written in Swift.

🤖📐专为数学建模设计的 Agent & skills ,自动完成数学建模,生成一份完整的可以直接提交的论文。 An Agent Designed for Mathematical Modeling ,Automatically complete mathmodel and generate a complete paper ready for submission.

The Windows App SDK empowers all Windows desktop apps with modern Windows UI, APIs, and platform features, including back-compat support, shipped via NuGet.

luban是一个强大、易用、优雅、稳定的游戏配置解决方案。luban is a powerful, easy-to-use, elegant and stable game configuration solution.

🌍 📖 A readable, automated, and optimized (2 kb) internationalization for JavaScript

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

autonomous harness engineering

Fully Open Framework for Democratized Multimodal Training

一个本地优先、可被 AI Agent 调用并持续维护的个人知识库,以及它的可视化 Workbench。

Rust-first autonomous agent runtime with functional parity goals against NousResearch/hermes-agent, plus an Ultra reliability, security, and operator-control layer.