# Xiaomi smart home MCP server

> Use this tool when you need to control Xiaomi/Mijia smart home devices using natural language, enabling AI agents to turn conversations into physical actions in real-time. It solves problems of smart home automation and voice control, allowing for seamless interaction with devices. The tool takes natural language inputs and outputs device control commands, making it ideal for use cases where voice assistants or AI agents need to interface with smart home devices.

Canonical page: https://skillsregistry.net/skills/handsomejustin-mijia-control  
JSON: https://api.skillsregistry.net/v1/skills/handsomejustin-mijia-control

## Description

mijia-control

A production-ready MCP server that enables AI agents (Claude Code, Claude Desktop, Cursor, Hermes, etc.) to directly control Xiaomi/Mijia smart home devices through natural language.

What it does

Turns conversations into physical actions — "turn on the desk lamp to 50%" becomes actual device control in real-time.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/msjfhufrrt)
- **Repository:** <https://github.com/handsomejustin/mijia-control>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "handsomejustin-mijia-control"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/handsomejustin-mijia-control` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/handsomejustin-mijia-control/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt