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

MCP桥接浏览器插件,让网页端的AI具备调用MCP工具的能力

A production-ready MCP (Model Context Protocol) server that enables to control Blender directly through natural language.

AI powered automation toolkit which acts as an agent that discovers MCP servers for you. Point it at GitHub/npm/configure your own discovery, let GPT or Claude analyze the API or MCP or any tool, get...

A TypeScript example showcasing the integration of Ollama with the Model Context Protocol (MCP) servers.

is a Python package that implements a Model Context Protocol (MCP) server, designed to dynamically expose REST APIs—defined by OpenAPI specifications—as MCP tools.

Convert any MCP server into a Claude Skill with 90% context savings.

🚀 Intelligent MCP server bridging Claude AI with Dash (macOS documentation browser). Transforms local Dash docsets into context-aware documentation assistant with fuzzy search, project detection,...

A powerful Model Context Protocol (MCP) server that provides seamless integration with Google Drive, allowing AI models to search, list, and read files from Google Drive.

MCP OAuth Proxy is an open-source OAuth 2.1 proxy server that adds authentication and authorization to MCP (Model Context Protocol) servers.

An MCP (Model Context Protocol) server for interacting with LSP (Language Server Protocol) interface. This server acts as a bridge that allows LLMs to query LSP Hover and Completion providers.

This is an MCP (Model Context Protocol) server that gives Claude the ability to see and interact with any macOS application - just like Playwright does for web browsers, but for native Mac apps.

The Python brain behind the Dive desktop app — also runnable standalone as a service or library.
Agent Skills

image-to-code is a Codex skill for turning a selected UI image, screenshot, or Figma export into an adaptive code implementation, high-density transparent PNG assets, and optional editable Figma...

Portable for writing ML/AI academic papers — from topic to compiled PDF, with verified BibTeX citations, gated workflows, and multi-agent collaboration.

🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报

Readable RTL → clear behavior → reviewable delivery Give AI the design intent, review the behavior preview, and receive artifacts you can inspect and verify.

macOS arm64/x86_64 and Linux x86_64/arm64. Single binary, no runtime deps.

CLI for the Google Health API v4 — built for AI agents and developers.

这是一个 ,让 AI 能够使用 IDA Pro 自动分析恶意软件,就像人类安全分析师一样:

Forge Nature-level scientific panels into executable plotting code. Retrieve open-access papers, split full figures into reviewed panels, classify them with Qwen, and reproduce statistical panels...

OpenBKN is an ontology-driven business knowledge network platform. Through ontology modeling, it turns the data and logic scattered across documents, systems, processes, rules, and expert experience...

We welcome issues and pull requests for missing work on harness agents, agent skills, memory, self-improvement, agent RL, evaluation, and safety.

MoChat: Reconnecting the World through AI Agents

The first browser AI Agent extension to support Agent Skills, enabling AI to perform complex tasks through an expandable skill system. 🌟 Star if you like it!