Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
一个基于 MCP（Model Context Protocol）协议的智能宠物伴侣应用，通过语音识别和自然语言处理技术，为宠物主人提供实时互动和服务。该应用是一个 MCP-Client 应用，可以自主无限搭配 MCP-Server 实现需求。
Generate an MCP for any web app
Skill and MCP server for searching and retrieving icons
Automated AI code reviews powered by Claude Code. Assign a reviewer on your merge request — Claude reviews the code, tracks progress in real time, and follows up when you push fixes.
is a minimalist implementation of agents powered by LLMs and Model Context Protocol (MCP) tools.
A collection of Model Context Protocol (MCP) servers for integrating with various IT service management and remote monitoring platforms.
MCP Server Unified Deployment Open Source Project
An MCP (Model Context Protocol) server designed to interact with an Abaqus/CAE Graphical User Interface (GUI).
A Model Context Protocol (MCP) server that provides AI assistants with the ability to interact with Ansys simulation software.
A flexible gateway server that bridges Model Context Protocol (MCP) STDIO servers to MCP HTTP+SSE and REST API, enabling multi-instance MCP servers to be exposed over HTTP.
Showing how to transition from a naive agent to an MCP agent in 3 steps
An MCP (Model Context Protocol) server providing LLM agents with direct access to NASA's Common Metadata Repository (CMR).
Agent Skills
是一个 Claude Code 插件，基于 WooYun（2010-2016）收录的 22,132 个业务逻辑漏洞案例，为 Claude 的安全测试输出注入**、**和**。
Bridge between LLM-Agent and Cadence Virtuoso. A new infrastructure for Agentic Analog and Mixed-Signal Design.
Hierarchical agent loops with recursive self-organization.
Claude Code skill for premium scroll-driven websites. Scroll becomes the timeline, on a real design floor, verified by screenshotting its own scroll.
Canary QA harness built for Claude Code.
Claude Code+Obsidian，邪修读论文就是快
English · 简体中文 · Project Rules · Initial Prompt · 📧 Contact
An open-source, self-hosted AI code review bot powered by Vercel.
Topic → 4K narrated video for coding agents. v4.0: all TTS via the ttsCN engine component (11 platforms incl.
ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent
Everything for pentest. | 渗透测试知识库，以 AI Agent 可执行的格式沉淀安全方法论。
BMAD-METHOD planning + Ralph autonomous implementation, wired through platform-specific instructions, skills, and command indexes.