No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by javen-yan · MCP Server · ★ 64
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is miot-mcp safe to install? View the security audit →
米家 MCP Server 中文文档 | English 一个基于 的产品化米家 MCP 服务。它不再要求客户端先理解 、 这些协议细节，而是优先面向“家庭、房间、设备名、场景名”提供更自然的查询和控制能力。 这版解决什么问题 面向 AI 客户端：优先暴露稳定、清晰的产品级工具，而不是底层协议字段 面向真实家庭场景：先看家庭与房间，再定位设备，再执行控制 面向 MCP 标准：工具返回结构化结果，服务状态和登录状态可直接被客户端消费 面向扩展：标准能力 schema、profile 驱动控制、资源模型可以继续演进 当前能力 服务与登录 家庭与设备 设备控制 场景与耗材 MCP 资源 安装 建议使用 Python 。 如果你不用 Poetry： 启动 测试握手： 登录方式 已移除账号密码登录，只支持二维码登录。 首次需要登录时，服务会： 生成浏览器页： 同时生成二维码图片： 默认优先用系统浏览器打开 只有浏览器打不开时，才回退到图片查看器或终端二维码 认证信息会保存到： text /.miot-mcp/authdata.js
| Stars | 64 |
| Forks | 11 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 60.5194612974043/100 |
| Last Updated | 2026-08-14 |
| Created | 2025-08-20 |
| Platforms | mcp, python |
| Est. Tokens | ~13k |
These tools work well together with miot-mcp for enhanced workflows:
Looking for a miot-mcp alternative? If you're comparing miot-mcp with other mcp server tools, these 1 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MijiaPilot - 小米-米家生态 × MCP × CLI x AI Agent × HomeKit 全桥接家庭智能家居平台。
Explore other popular mcp server tools:
miot-mcp is 基于 MijiaAPI 的米家设备智能控制代理，提供标准化的 MCP 服务，支持动态设备发现、属性读写和动作调用. It is categorized as a MCP Server with 64 GitHub stars.
miot-mcp is primarily written in Python. It covers topics such as mcp-server, mijia, xiaomi.
You can find installation instructions and usage details in the miot-mcp GitHub repository at github.com/javen-yan/miot-mcp. The project has 64 stars and 11 forks, indicating an active community.
miot-mcp is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to miot-mcp on Agent Skills Hub include mijia-control. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: