Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers
PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human
Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation
Please see the updated mcpb format Claude Desktop Extension
Open-source AI podcast clipper. Turn a long episode into short clips with face tracking and burned-in captions. Drive it from the CLI, a web studio, or your coding agent.
Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code review. Supports Claude, Codex, Gemini, OpenCode and Aider.
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
Perplexity Advanced MCP is an advanced integration package that leverages the OpenRouter and Perplexity APIs to provide enhanced query processing capabilities.
Autonomous agents that find your clients on LinkedIn, on a server you own. An MCP server with 26 tools, so Claude or Cursor can run it. Self hosted LinkedIn outreach, AGPL, one command install.
Build WordPress sites with your AI
Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.
MCP server for Things 3 via Things Cloud API
Use Devnors Data from Python with one API Key.
Agent Skills
让 AI 按投行标准写行业研究报告：系统的分析框架 + 可溯源的数据 + 透明的计算过程 + 诚实的不确定性披露。
A collection of Claude Code skills for code review and design guidance based on Clean Architecture principles and Kent Beck's refactoring philosophy.
DeepAgent 기반 Research(연구) Multi Agent System 구축 - Context Engineering
axi-front-design 是一个 Claude Code Skill，让 Claude 扮演**而非通用前端工程师——用 HTML 产出落地页、幻灯片、交互原型、动画、信息图、移动端 Mockup 等高保真设计稿。
An open-source , , and for AI agents. Empower your agent to generate images, videos, sound effects, and music on their own.
投研报告精读助手 - Claude Skill for systematic analysis of investment research reports
基于 Claude Code Agent Teams 的多智能体协作安全审计框架，覆盖环境构建、静态侦察、动态追踪、深度对抗利用、后渗透关联分析、报告收口全链路，支持 专家级审计。
API rate-limit docs: quotas, headers, 429, backoff — predictable tone.
把上游 zhaoxuya520/reverse-skill（27k★，MIT）全部 原样封装成一个 dsh Cordis 插件，随包分发、随插件加载，无需手动维护候选清单。
抖音作品发布前的 工具。 粘贴你的口播文案 → 一键查出违规风险、给出最小改动建议、并按赛道权重打出"流量潜力分"。
一个 Claude Code , 可直接使用的科研写作指导,覆盖写作、修改、评审与报告——。
面向 AI 产品实习求职、转行和个人项目包装的交互式 AI 辅导 Skill