Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers

⚠️ :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。

Yet Another Frida MCP Server - Full-featured MCP server for Frida dynamic instrumentation

Headless Blender automation via FastMCP — 41 portmanteau tools (150+ ops). Batch mesh/VSE/Grease Pencil, VRM, Gaussian splats; optional live bridge. For Cursor / Claude Desktop.

MD2Card Markdown 转知识卡片 将 Markdown 文档转换为精美的知识卡片,支持多种风格

Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.

本项目面向** —— 如果你的 AI 伴侣住在 rikkahub 之类的 MCP 客户端里,本服务可以让 TA 真的"触碰"到你:通过 MCP 协议一句话控制你手里的 智能玩具。

密探渗透测试工具包含资产信息收集,子域名爆破,搜索语法,资产测绘(聚合测绘,FO FA,Hunter,Quake,Zoomeye,DayDayMap,censys,shodan, 零零信安),指纹识别,敏感信息采集,文件扫描、端口扫描、弱口令破解、jwt密钥爆破、Sessionkey,heapdump, 微信小程序,密码本,随机用户,社工字典,AI渗透(MCP、代码审计)等功能

Please see the updated mcpb format Claude Desktop Extension

Local academic paper tool MCP server — , multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

Bring your AI to life—talk to assistants instantly in your browser. Compatible with Claude Desktop, OpenCode, and other MCP-enabled AI tools.

Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
Agent Skills

Continuous code review for AI coding agents. roborev runs in the background, reviews every commit as agents write code, and surfaces issues in seconds -- before they compound.

Get your animations easily done with only Tailwind CSS classes.

is an API-first Ruby web framework that combines the developer experience of Rails with fiber-based concurrency.

Your AI skills and agents, finally organized.

A collection of AI agent skills focused on resume optimization, job applications, and career development.

SkillsBench evaluates how well skills work and how effective agents are at using them.

本仓库目前继续保持公开访问,暂不归档或删除,但已停止功能与兼容性更新。后续开发、版本发布和问题修复均已迁移至 。建议所有新老用户下载并使用新项目。 项目主页 / Project home · 最新版本下载 / Latest release This repository remains publicly accessible and is not being archived or...

A better whois and domain intelligence toolkit. Interactive TUI with tabbed views for WHOIS, DNS, mail, SSL/TLS, HTTP headers, SEO analysis, and tech stack detection.

A compiler-first reactive JavaScript UI framework. No virtual DOM. Compile-time JSX transforms. Proxy-based stores. Surgical DOM patching.

A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery.

🇮🇷 Persian Tools — The Complete TypeScript Toolkit for Persian (Farsi) Apps A comprehensive, library-agnostic TypeScript toolkit for Persian (Farsi) text, numbers, validation, and locale utilities...

:mortar_board: → Explore all DeepLearning.AI courses — taught by the people building the future of AI. Find your next one. :computer: → Browse the DeepLearning.