Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
claude mcp add native-devtools -- npx -y native-devtools-mcp
MCP server providing read-only access to Quicken For Mac financial data via Claude
An MCP server for web search using DuckDuckGo and content extraction, with support for multiple URLs and memory optimizations.
Built-in MCP chat, tool server, and browser bridge for controlling ComfyUI.
(Claude, Cursor, Cline, Windsurf, Zed, etc.)
An MCP server that enables Claude Desktop, Claude Code, Cursor, or other MCP clients to directly access and process arXiv papers by fetching the LaTeX source.
You make a commit. Weeks later you wonder: "Why did I write it this way?"
Compass is an MCP server that gives Claude shared operational state across all three surfaces. Add a task in Chat, check it off in Code, filter by project in Cowork — same data, zero re-explaining.
In celebration of getting 52 GitHub stars, mcp-webcam 0.2.0 is here! Now supports streamable-http!! No installation required! - try it now at https://webcam.fast-agent.ai/.
Manage WordPress sites with natural language through AI tools like Claude Desktop
通用 AI 搜索 MCP 服务器，支持任何兼容 OpenAI API 格式的 AI 模型进行联网搜索。
MCP server for using the REMnux malware analysis toolkit via AI assistants.
Agent Skills
The skill manager for AI coding agents. Install, update, and sync skills across Claude Code, Cursor, Copilot + more.
Readable RTL → clear behavior → reviewable delivery Give AI the design intent, review the behavior preview, and receive artifacts you can inspect and verify.
GitHub CLI for agents — designed with AXI (Agent eXperience Interface).
🧠 Skill Generator Ultra The most comprehensive AI Skill creation toolkit on the market. Bộ công cụ tạo AI Skill toàn diện nhất trên thị trường.
is an MCP server that turns Claude-style skills (SKILL.md plus optional resources) into callable tools for any MCP client.
OpenYida connects AI coding agents with Yida's low-code platform, so developers can create apps, forms, workflows, custom pages, reports, integrations, and deployment configuration from a normal...
Hey everyone, Divergent AI here! I'm super happy that I'm seeing the project getting some love. It's motivated me to come back at it with a really strong update for you all.
一个安全测试专家技能（Agent Skill），将 WooYun 88,636 个真实漏洞案例、先知 5,600+ 篇研究文档、GAARM 173 条 AI 安全风险（5 域）、OWASP LLM/ASI/WSTG 三大框架与 200+ 常用测试用例，浓缩为可按需加载的实战渗透测试知识库——让 AI 助手在安全评估中即时调用系统化的攻防知识。
"The first principle is that you must not fool yourself — and you are the easiest person to fool."
- ❌ ：GPTZero、Originality.ai 等工具检测出 AI 生成痕迹 - ❌ ：知网、维普等平台查重率过高 - ❌ ：语言风格不符合学术规范，逻辑不够严谨 - ❌ ：手动修改效率低，难以追踪优化进度
The skills here are built from this source into a portable Agent Plugin and installable client-specific plugins for Claude Code, Cursor, Codex, and Grok — install one of those, not this repo.
An agent that directs Seedance 2.0 like a filmmaker — reading each scene before it writes the prompt.