Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents
Real reap --agent output, run against a generated sample stack ( hero-fixture.sh ) — not anyone's install. The numbers further down are measured on mine.
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件，读取文档、发送消息、合同审批、数据处理.....
IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
Generic markdown vault MCP with hybrid search
Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.
Vibe-code your game development remotely from anywhere! 🌍 이제 집밖에서도 원격으로 바이브코딩으로 게임 개발 가능합니다! 🎮
Personal finance, keyboard-first. Available as a or a — both running over the same local data: Plaid sync, CSV import, categorize, tag, search, analyze.
The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.
Agent Skills
上传一张图片，AI 分析后生成结构化 JSON + 平文本提示词，可用于还原/复刻该图片。
AI Skills for Everyone：人人都能用的开源 AI 技能库（⚠️ Alpha内测版）
Yi3D is a simple and easy-to-use 3D modeling application, available on Windows and Linux.
Architecture Decision Records as executable specifications for coding agents. An agent reads the ADR and implements the decision. A human reviews and approves.
把日常、照片、知识、会议和长文，持续收进按月成册的漫画手帐。
A Claude Code skill that builds, signs, and submits Flutter/iOS apps to App Store Connect — end to end, from flutter build to WAITING_FOR_REVIEW.
Your agent (Claude Code, or any Skills-capable harness) plays orchestrator: it sequences an approved plan, briefs OpenAI Codex to write all the product code, reviews every diff, runs the test gate,...
: Provides the agent with a classical formal-logic framework based on G. Chelpanov's textbook («Учебник логики»).
A Claude Code skill that transforms vague AI prompts into clear, specific, actionable ones using Aristotelian first-principles reasoning.
Persistent project memory and session lifecycle management for Claude Code.
The is an open standard that defines what "AI-ready" actually means — six factors, 62 measurable requirements, and five workload profiles that apply to any data platform.
✨ - Type #snippet anywhere in your message and watch it transform.