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

Fleet memory for AI agents — governed, shared, self-improving.

MCP Server implementation for Ableton Live OSC control

A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.

A Model Context Protocol (MCP) server that connects OmniFocus to Claude and other MCP-compatible AI assistants.

Apache Doris MCP Server

For MCP users, lets LLM clients such as Cursor and Claude Code design Cisco-style networks directly through Model Context Protocol tool calls.

MCP Server for code graph analysis and visualization by CodeGPT

The Official MCP package for Dokploy

allows you to control from using the . It consists of:

Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.

Neo4j official MCP Server

A Model Context Protocol (MCP) server for Microsoft SQL Server that enables secure database interactions through a controlled interface.
Agent Skills

![Very Good Ventures][very_good_ventures_link_dark] ![Very Good Ventures][very_good_ventures_link_light]

Claude Code skills for auditing, cleaning, enriching, and automating your HubSpot CRM

它把角色卡、会话记忆、知识库、成员目录、技能系统、模型接入、Web Console,以及 OpenClaw 兼容 skill runtime 都收敛在同一个服务里;NapCat / OneBot 只负责 QQ 协议和消息收发。

Summarize a paper with the FOCUS method

上传你和 crush 的聊天记录,AI 模拟 ta 的性格,你在安全沙盒里反复练习——找到真诚又有效的沟通方式。 Upload your chat history with your crush. AI simulates their personality. Practice in a safe sandbox until you find your voice.

让你的 coding agent 的技能,从每一次真实会话里自我进化——你只管写代码。

- 与 是 skill 模式(被支持 Skills 的 IDE 加载执行),仅依赖可读的小程序源码目录 - 是独立的 Node 工程(含 CLI / Web UI),依赖 Node ≥ 18.17

is an open set of skills for the : proven instructions, workflows, and examples that help AI agents work with Spring Boot projects predictably.

林月半子的 AI 开源技能库,持续更新中。

Codex/Claude skill for generating bilingual-ready AI short-video scripts with frameworks, hooks, and examples.

Clawdbot skills for agentic coding workflows - ACFS stack, cloud CLIs, and dev tools

多智能体协作,将研究问题转化为专业级研究报告 —— 每一个数据点都经过交叉验证。