Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).
An MCP App for playing and inspecting local audio files in an MCP host.
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time.
Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built...
MCP Server for Authentication Management
Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.
parallel-browser-mcp is an MCP server for parallel browser automation. It exposes a numeric session model over MCP so one client can create and control multiple browser sessions at the same time...
🌉 Local-first Proton Mail MCP and CLI through Proton Bridge. Search, read, draft, send, sync, and act on mail from Claude Desktop or Terminal.
A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.
MCP server providing isolated sandbox environments for AI agents.
ArkTS/ArkUI 开发助手 MCP Server，为 AI 编程助手（Claude Code、Cursor、Windsurf 等）提供文档检索和华为官方智能问答能力。
FocusRelay is a fast, native Swift MCP server and CLI that helps AI assistants read and safely update OmniFocus using documented OmniFocus APIs.
Agent Skills
AI 塔罗占卜 Agent Skill，为 Cursor / Claude Code / OpenClaw 等 AI agent 提供专业级塔罗解读能力。
A complete task manager for Claude Code and Codex — and the working memory layer that turns every session from a brilliant new hire into the engineer on your team.
SkillCorpus is EverMind's open-source pipeline for turning scattered SKILL.md files from public repositories into reliable agent context.
一个面向 Codex 的产品 UI 设计评审 Skill。它会像公司里的设计专家团一样，从视觉质量、交互体验和设计系统三个层面检查设计稿，输出去重、按优先级排序、可执行的优化建议。
One teacher. One mind. Portable agent skills that run Eero Alvar’s AI learning loop.
Apple docs. WWDC26 transcripts. Semantic + keyword + hybrid search. One clean tool.
Скилл для ИИ-агентов: находит и убирает следы машинной генерации в русскоязычном тексте. Переписывает «гпт-шный» текст по-человечески, не искажая смысла, и не трогает живое: ложное срабатывание здесь...
The design language of Open Analytics, packaged three ways: an agent skill, type-checked component recipes, and a CLI.
P-ACP is a private agent commerce protocol for autonomous agents to discover services, negotiate encrypted work terms, authorize wallet settlement, exchange sealed deliverables, and publish...
A workflow toolkit that turns any AI coding assistant into a disciplined engineering partner — proposal to archive, tracked and reviewable.
- A modern biomedical knowledge graph with molecular, anatomical, clinical, and environmental modalities.
CS Skills 是陈硕在真实项目中沉淀的一组 Codex AI Agent 工作流。