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
⚠️ ：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
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A collection of interesting libraries and tools for Avalonia project.
Xiaomi Miloco
Skills for the Gemini API, SDK and model/agent interactions
Write HTML. Render video. Built for agents.
专业的短剧剧本创作skill,从选题立项到分集撰写、质量自检、合规审核、海外出海，覆盖短剧剧本生产全流程。
Copy this repo into any project. Claude Code, Codex, and other agentic tools then follow the same gated process — spec, plan, task cards, implementation, verification, review — before code reaches...
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
The first UI framework for the agentic era — tiny, performant, with WASM sandboxes for safe code execution.
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and...
Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message