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
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
MCP Server for Ozon marketplace - search products, get details, prices and delivery info
Scan your dev machine for AI agents, MCP servers, IDE extensions, suspicious files, and risky package-manager configs — in seconds.
kali linux mcp,pentest,penetration test
A mcp server that bridges Dune Analytics data to AI agents.
Add vision to text-only models in Opencode (, ) — , no manual file saving.
台灣醫療健康資料整合 MCP 伺服器 整合 ICD-10-CM/PCS、SNOMED CT、LOINC、台灣 FDA 藥品 / 健康補充品 / 食品營養，以及 FHIR R4 IG 授權與驗證工具
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
MCPSafari: Native Safari MCP Server for AI Agents
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.
This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:
The polished public release — native ComfyUI design system, live activity cards for every agent edit, and multi-tab support. Search in ComfyUI-Manager to install, or see the docs.
Agent Skills
生成AIを用いて大量生産された、低品質で中身を伴わないコンテンツを指す俗語です。
Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.
A skill that turns any goal into one short, paste-ready prompt. That prompt makes your agent pick a real quality bar, split the work into small pieces, run a builder and a separate harsh critic on...
AI defaults to the mean. Models are trained on millions of average websites. If you don't constrain them, they will build an average website.
주요정보통신기반시설(CII) 취약점 분석평가, AI 보안 평가, 로봇 보안 점검, 우주 보안 점검, 시큐어코딩 가이드, 제로트러스트 보안 평가, SW 공급망 보안(SBOM)을 위한 Claude Code 스킬 플러그인입니다.
这里收的东西，目标都很直接： - 能单独看懂 - 能尽快跑起来 - 能在真实工作流里省时间
· Next-Gen Transparent Agent Architecture
合乎周礼 是一个中文梗文案生成器，也是一个周礼体反向解释器。它支持两种方向： 问礼时，把普通中文改写成“大周礼时代”流行的白话翻译腔；释礼时，把周礼体翻回直接人话。 问礼会先讲一个看似古代的道理，再把现代小事放进礼法、名分、职分和体面里一本正经地论证； 释礼会拆掉这些包装，只保留原文真正想表达的意思。
One memory, not one per tool. A centralised, plain-text memory layer shared across all your AI agents and projects.
AEnvironment Everything as Environment — A Production-Grade Environment Platform for Agentic RL and Agent
31 skills for Claude Code covering the full academic research paper lifecycle — from literature search to slide generation — plus GitHub repository analysis for research topics.
gentle-pi installs in Pi: a senior-architect operating layer for Spec-Driven Development, focused subagents, strict TDD evidence, reviewable work units, safety guards, project/user skill discovery,...