Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.
MCPSafari: Native Safari MCP Server for AI Agents
A progressive AI Agent Harness tutorial written in Rust.
RimBridgeServer runs an MCP server inside RimWorld so AI agents and external tools can remotely control and observe a running game.
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.
kali linux mcp,pentest,penetration test
MCP Server for Ozon marketplace - search products, get details, prices and delivery info
Streamable HTTP MCP server for Claude.ai custom connectors.
A secure Windows SSH workspace and MCP server for Codex, Claude Code, Cursor and other AI agents.
Open-source SAST engine that traces vulnerabilities across files and functions
An MCP server that provides access to LLMs using the LlamaIndexTS library.
Agent Skills
NAS媒体库自动化管理工具
中国软件著作权申请材料 生成器 Skills，本 Skills 通过阅读本地项目，自动生成全套 .docx 软著申请材料，全开源，无须再付费购买任何软著申请服务
Local-first Obsidian knowledge ingestion workbench for PDFs, Markdown, TXT and spreadsheets.
A local minimized harness, with simplified output and logs for self-evolve
Central marketplace for Claude Code plugins by xiaolai
(formerly "AI Shortcuts") is a browser extension that lets you compare answers from multiple AI models in one place.
Custom extensions and skills for pi coding agent.
Collection of components and sections specifically designed for creating landing pages with Nuxt 4 and Nuxt UI.
QuantManus 是一个基于大语言模型（LLM）的智能 Agent 框架，专注于**、**和**。
We are moving from "prompt as text" to . Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be...
Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.
开发真正的应用很难。GSD、BMAD、Spec-Kit 等方法试图通过接管流程来帮忙。但在这么做的同时，它们剥夺了你的控制权，并且让流程中的 bug 极难排查。