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

Turbular is an open-source Model Context Protocol (MCP) server that enables seamless database connectivity for Language Models (LLMs).

Kernel-level sandboxing for LLM agent tool calls made through the Model Context Protocol (MCP).

Complete agent workflow: user input → tool approval → execution → streaming response

Model Context Protocol server enabling AI assistants and chatbots to access transit information through standardized interfaces.

这是一个基于MCP (Model Context Protocol)的智能信息获取服务器,为AI助手系统提供强大的搜索能力和面向LLM优化的网页内容理解功能。通过多引擎搜索和智能内容提取,帮助AI系统高效获取和理解互联网信息,将网页内容转换为最适合LLM处理的格式。

"The question is not what you look at, but what you see." — Henry David Thoreau

A local, modular Retrieval-Augmented Generation (RAG) system using the Model Context Protocol (MCP) to connect an LLM to external tools like vector databases and document loaders.

Create production-ready MCP servers in PHP with modern architecture, and flexible transport options.

Anthropic’s Model Context Protocol implementation for Oat++

provides a secure and verifiable method to uniquely identify agents through open and decentralized techniques.

一个高性能的文档转换服务器,同时支持 和 接口。将 PDF、Word 和 Excel 文档转换为 Markdown 格式,具备图片提取、页眉页脚移除和批量处理等高级功能。

A Go-based plugin for Unraid that exposes comprehensive system monitoring and control via REST API and WebSockets.
Agent Skills

一个用于 Codex 的双图版旅行记忆卡技能。输入一张照片后,它会输出两张彼此匹配的图片:

Every time you debug an error with an AI agent, that knowledge vanishes when the session ends. captures it — automatically building a searchable knowledge base that evolves project rules over time.

Collection of Agent Skills for Autodesk Platform Services.

Google Maps Platform agent skills are portable, self-contained modules of Google Maps Platform-specific knowledge, instructions, and workflows.

Una colección de Claude Skills en español para potenciar tus flujos de trabajo con Claude AI.

OSS legal workflows in the form of portable SKILL.md files

缠论(缠中说禅)技能库 - 基于 waditu/czsc 库的 Claude Skills

design-image-studio 是一个面向创意与设计场景的 Agent Skill。它不是简单地把一句话塞给文生图模型,而是先读取并保留完整的 Claude 设计系统提示词,再把需求整理成设计推理和结构化 brief,最后把这些设计判断压缩成更强的生图 Prompt,并直接调用 Volcengine Seedream 生成图片。

opentraces hub — reach out for early access

stands for . The npm package and repository slug bmad-method-test-architecture-enterprise is a package name and never an expansion of the acronym.

My agent skills that I use every day to do real engineering - not vibe coding.

面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑,覆盖内容创作、设计视觉、工具集成、合规文书等场景。