Exposes Zigbee2MQTT devices through MCP, enabling AI assistants and agents to discover, monitor, and control connected Zigbee devices such as lights, switches, sensors, plugs, and thermostats without interacting directly with Zigbee2MQTT.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Oremi Iṣakoso turn off the living room lights"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Oremi Iṣakoso is an MCP server for smart home control. It exposes Zigbee2MQTT devices through the Model Context Protocol (MCP), enabling AI assistants and autonomous agents to discover, monitor, and control connected devices using a standardized interface.
Built with FastAPI and designed to run in Docker, Oremi Iṣakoso provides secure, reliable, and real-time access to lights, switches, sensors, plugs, thermostats, and other Zigbee devices without requiring agents to interact directly with Zigbee2MQTT.
The name Oremi Iṣakoso comes from the Yoruba language. Oremi means "my friend", reflecting the project's goal of building a helpful and trustworthy AI ecosystem. Iṣakoso means "control" or "management", representing the service's responsibility for managing and controlling smart home devices through a unified MCP interface.
All project documentation—including architecture details, configuration reference, and the Home Assistant integration guide—can be found at: https://demsking.gitlab.io/oremi-isakoso/
Related MCP server: ZigBee2MQTT MCP Server
Oremi Iṣakoso is built with Python and uses uv for dependency management. The
project follows standard Python development practices with type hints, linting,
and automated testing.
For detailed information on setting up your development environment, running tests, code style guidelines, and the pull request process, please refer to CONTRIBUTING.md.
This project adheres to Semantic Versioning (SemVer).
Version numbers follow the MAJOR.MINOR.PATCH format:
MAJOR version increments for incompatible API changes
MINOR version increments for backward-compatible new functionality
PATCH version increments for backward-compatible bug fixes
Copyright 2026 Sébastien Demanou. All Rights Reserved.
Licensed under the Apache License, Version 2.0. See the LICENSE for the complete license text.
This server cannot be deployed
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth).
