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

🚀 Apache RocketMQ built in Rust 🦀 — faster, safer, and more memory-efficient. Powering high-performance messaging for the AI era, with AI Agent, MCP, and AI-SRE capabilities.

LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.

The official MCP server implementation for the Perplexity API Platform

Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.

The TypeScript MCP framework

淘宝联盟,京东联盟,多多进定全平台 MCP 服务是一个基于 Model Context Protocol (MCP) 的服务,支持淘宝、拼多多三大电商平台的链接转换和商品推广功能,商品搜索等等一系列工具

MCP Documentation Management Service - A Model Context Protocol implementation for documentation management

MCP Python Tutorial

A Model Context Protocol (MCP) server implementation for Todoist integration, specifically developed for Cursor AI.

这是一个基于 MCP (Model Context Protocol) 的邮件工具,它能让 AI 模型通过标准化接口访问电子邮件服务。

AI companion for FIFA World Cup 2026 — 18 tools covering matches, teams, venues, city guides, fan zones, visa info, head-to-head records, and more. Works with Claude, ChatGPT, Cursor, and Telegram.

Conecte qualquer assistente de IA ao DataJud CNJ e aos 91 tribunais brasileiros - com cálculo de prazos, monitoramento de processos e conformidade com o CPC.
Agent Skills

AI를위한JSONUI마스터

A professional research suite for conducting rigorous academic research using specialized agents and multi-platform CLI commands. Compatible with , , , and .

Resume builder for academics and engineers

YYLO (why-lo): AI coding-agent orchestration CLI with equivalent yylo and yy launchers.

ClawSync, OpenClaw for the cloud. Deploy an open source personal AI agent with chat UI, skills system, MCP support, and multi-model routing. Built on Convex.

原 [chatlog]项目(一个微信数据库解密读取及提供mcp服务、http服务的开源软件),现已支持通过微信clawbot接口推送消息,可以实时转发全部或指定消息到clawbot

The open sharing protocol for the agentic era. A Linux Foundation AI & Data Project

这个仓库源于我使用 Codex 的日常需求。写论文不是单点任务,而是一条从构思、实验、写作、审稿到 rebuttal 的长链路;每一步都需要 AI 有边界、有证据、懂学术表达。因此这个仓库把 组织成当前 7 个模块、27 个可触发 Skills:

Reverse-engineer any design system into a Claude-ready skill. Pure static analysis. No AI. No API keys.

Production-ready skill for building, testing, and automating iOS apps. 27 scripts optimized for both human developers and AI agents.

- 작성자: 정구봉 - LinkedIn: https://www.linkedin.com/in/gb-jeong/ - 이메일: [email protected]

Companion repo to our livestream series Show Us Your (Agent) Skills