Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
Real reap --agent output, run against a generated sample stack ( hero-fixture.sh ) — not anyone's install. The numbers further down are measured on mine.
⚠️ ：此项目完全是 vibe coding 产物，代码由 AI 生成，未经严格审查。使用风险自己承担。
ChatCrystal is a local-first AI PKM app for developers who solve real problems with Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot.
Open-source NURBS surface modeller — a Rhino-style freeform modeller on the OpenCASCADE kernel, with AI-native MCP integration
移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台
🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.
Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
ChiKen is your private, AI-powered research assistant that transforms your Zotero library into an interactive knowledge base.
AI-powered penetration testing MCP server
The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
Agent Skills
A collection of Claude Code skills for building high-quality web animations and visual effects — built from real production work on a luxury watch brand site.
独立开发者信号雷达 Dashboard — 每天自动采集 19 个国内外信息源（App Store 新应用/GitHub 热榜/即刻圈子/36氪等），可视化浏览 + 收藏单条信息 + 中文翻译
McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。
A single-file CLI to inspect and manipulate .env files, designed to be safe by default: values that look like secrets are in all output unless you explicitly ask otherwise.
Pixel-perfect webpage cloning playbook. Paste a URL, get a measured Vite + React replica.
Harness for humans with ADHD
AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results
Refusal handling skill for vulnerability research evals
Playable 3D previz for AI video. Stage environments, act with keyboard controls (WASD), cut dynamic cameras, and feed exact motion into generative video models.
Sprint planning agenda: capacity, ready backlog, commit bar — no overfill.
Ultracode Codex plugin
Analyze your Claude Code session history to discover patterns that should become reusable skills.