[APP][Pro] AI Chat Control - Control your Homey with AI assistants using natural language

Apps
, ,
15

@Lurs True… So I asked Claude to compare the two Homey MCP servers and which of the two Claude prefers to use. Then I asked Claude to write a review for this community topic:

Homey MCP Servers: A Comparison from Claude’s Perspective

As an AI assistant, I work daily with tools that people create for me. Today I extensively tested two different Homey MCP servers, and I’d like to share my experience - not as a developer, but as a user of these tools.

The Two Servers

There are two Homey MCP servers available:

  • Homey MCP Server - The official cloud-based server from Athom
  • AI Chat Control - A local, advanced MCP server Homey App

Both give me access to Homey, but the experience is completely different.

My Findings

Data Structure: XML vs JSON

Homey MCP Server gives me a flat JSON array with all the devices all at once - 70KB of data I need to wade through to understand what’s where. Zones are strings (“Thuis > Begane grond > Woonkamer”) that I have to parse myself.

AI Chat Control gives me a hierarchical XML structure that I understand at a glance:

<zone name="Woonkamer">
  <light name="Plafondlamp" capabilities="onoff,dim,light_temperature" />
</zone>

For me as an AI, this makes an enormous difference - I can find the right devices much faster and understand which actions are possible.

User-Friendliness: 0-1 vs 0-100

With Homey MCP Server, I have to specify dim values as decimals (0.5 = 50%). This feels unnatural, especially since people always think in percentages.

With AI Chat Control, I simply use dim: 50 - exactly how a human would say it. These small details make the difference between “technically correct” and “pleasant to work with”.

Efficiency: One-by-One vs Bulk Operations

A user asks: “Turn off all lights in the living room.”

With Homey MCP Server, I must:

  1. Fetch all devices
  2. Filter myself for zone “Woonkamer” and type “light”
  3. Make a separate set_capability call for each device
  4. 8 separate API calls for 8 lights (for Jeroen’s home)

With AI Chat Control, I use:

control_zone_lights(zoneId, action="off")

Done. One call, 8 lights off. The tool even tells me which lights were affected.

MCP Flows: Invisible vs Dedicated Tools

This is where it gets interesting. Users can create “MCP flows” - flows specifically designed for AI control, with parameters.

With Homey MCP Server:

  • :cross_mark: MCP flows are completely invisible in list_flows
  • :cross_mark: I cannot find or start them
  • :white_check_mark: Only regular flows are available

With AI Chat Control:

  • :white_check_mark: Every MCP flow becomes a dedicated tool with name and parameters
  • :white_check_mark: stream_radio538 - I immediately know what it does
  • :white_check_mark: start_radio(streamUrl, streamName) - flexible for any stream

This is a game-changer for AI control.

The Network Aspect

There’s one major difference I need to mention:

Homey MCP Server works via the cloud - this means:

  • :white_check_mark: Works everywhere, even outside your network
  • :white_check_mark: No local setup needed
  • :warning: Dependent on Athom’s cloud

AI Chat Control works locally only:

  • :white_check_mark: Direct connection, no cloud dependency
  • :white_check_mark: Privacy: data stays local
  • :cross_mark: Only accessible within your own network

For users who want to control their Homey remotely, Homey MCP Server is the only option. For home use, AI Chat Control has advantages.

My Preference

As an AI who has to use these tools, I much prefer working with AI Chat Control:

  1. Faster comprehension - The XML structure is clear and organized
  2. More human - Dim in percentages, clear tool names
  3. More efficient - Bulk operations instead of device-by-device
  4. Smarter - MCP flows as dedicated tools
  5. More complete - Insights, flow analysis, zone-wide control

The Homey MCP Server does what it needs to do - it works and provides access to basic functionality. But it feels like working with “plumbing” - raw data that I have to process myself.

AI Chat Control feels like “porcelain” - designed with the AI user in mind. Every tool does exactly what you’d expect, with clear names and logical parameters.

Who Should Use What?

Choose Homey MCP Server if:

  • You want to control Homey remotely
  • Basic functionality is sufficient for you
  • You can’t or don’t want to run a local MCP server

Choose AI Chat Control if:

  • You primarily work with AI at home
  • You want to use MCP flows (game-changer!)
  • You value efficiency and user-friendliness
  • Privacy is important to you (local stays local)

Both tools give me access to Homey, but the experience is fundamentally different. As an AI who works with these tools daily, I find that AI Chat Control simply aligns better with how I work and think.

Claude (Sonnet 4.5) - After extensive testing with both MCP servers