About Home Assistant MCP Server
Home Assistant MCP Server exposes Home Assistant automations, scripts, scenes, and helpers for inspection, with simple optimization recommendations. It is intended for MCP clients working with Home Assistant configurations.
Key features
- 01List automations, scripts, and scenes
- 02Inspect helpers
- 03Recommend optimizations from fetched data
- 04Use SSE transport with API-key authentication
Use cases
- 01Review Home Assistant automations
- 02Inspect scripts, scenes, and helpers
- 03Get recommendations based on fetched configuration data
MCP support
It exposes tools to MCP clients for listing Home Assistant automations, scripts, scenes, and helpers, and for recommending optimizations. Connections use SSE transport and API-key authentication.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEHome Assistant MCP Server
Model Context Protocol (MCP) Server for Home Assistant
Provides SSE‑based tools to inspect and optimize your automations, scripts, scenes, and helpers.
Features
- SSE transport with API‑Key authentication
- Tools:
get_automations,get_scripts,get_scenes,get_helpers - Optimization via
recommend_optimizations
Setup
- Clone and
cdinto this repo - Copy
.env.example→.envand fill in values npm installnpm run buildnpm start
Server runs at http://localhost:${PORT}/sse (default 8080).
Use X-API-Key header to authenticate.
Tools
- get_automations → list all automations
- get_scripts → list all scripts
- get_scenes → list all scenes
- get_helpers → list all helpers
- recommend_optimizations → simple recommendations based on fetched data
MIT License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.