MCP server for Homey Pro: 60 tools for devices, flows, energy, and Z-Wave/Zigbee diagnostics.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-ringosystems-homey-wan-kenobi-mcp": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
MCP server for controlling Homey Pro smart home systems through the Model Context Protocol.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
knowledge_prompt_1Knowledge prompt for device control
knowledge_prompt_2Knowledge prompt for flow authoring and automation
knowledge_prompt_3Knowledge prompt for monitoring and troubleshooting
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in other
Pi Coding Agent extension (CLI-first) — routes bash/read/grep/find/ls through lean-ctx CLI for strong token savings. Optional MCP bridge can register advanced tools.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server
Autonomous spec-to-product coding-agent CLI with an MCP server exposing 34 tools over stdio.
MCP Security Weekly
Get CVE alerts and security updates for io.github.Ringosystems/homey-wan-kenobi-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
MCP server for controlling Homey Pro smart home systems through the Model Context Protocol.
The name nods to Obi-Wan Kenobi, your home's only hope for natural-language control.
60 tools and 3 knowledge prompts for device control, flow authoring, automation, monitoring, troubleshooting, network diagnostics, and self-hosted deployment.
Athom ships an official Homey MCP Server: a cloud-brokered remote connector you add to a paid Claude or ChatGPT plan and sign into with your Homey account. It covers device status and control, renaming and moving devices, creating, updating and starting Flows and Advanced Flows, and setting Moods.
This server differs in two ways. It is self-hosted, so you run it yourself over stdio or streamable-HTTP with no third-party broker and no paid AI-plan requirement. And it adds operational depth for power users that is not part of the official server's described capabilities.
The table reflects Athom's publicly described capabilities as of June 2026. Athom does not publish a formal tool list, so the right-hand gaps are inferred from their documentation, not stated by Athom.
| Capability | Official Homey MCP (mcp.athom.com) | Homey-Wan-Kenobi |
|---|---|---|
| Hosting | Cloud-brokered remote connector | Self-hosted, stdio or HTTP, no broker |
| Access | Paid Claude/ChatGPT connector plan | Any MCP client, no plan requirement |
| Devices, zones, control, rename, move | Yes | Yes |
| Flow and Advanced Flow authoring | Yes | Yes |
| Moods | Yes | Yes |
| Flow-card schema discovery (build flows from scratch) | Not described | Yes |
| Energy: live power and day/week/month/year reports | Not described | Yes |
| Insights: historical sensor and meter data | Not described | Yes |
| Z-Wave and Zigbee mesh diagnostics with remediations | Not described | Yes |
| App memory and usage analysis (removal candidates) | Not described | Yes |
| Infrastructure ops: backups, reboot, updates, memory, storage | Not described | Yes |
| Raw Homey Web API passthrough | Not described | Yes |
| Listed in the public MCP Registry | No | Yes |
diagnose_zwave_network and diagnose_zigbee_network read controller health, grade each node by last-seen age (battery-sleep aware), group transmit failures, correlate them with unavailable devices, and return severity-ranked remediations. get_zwave_log exposes the raw network log.analyze_app_usage cross-references every app against RAM, device counts and flow references to flag safe removal candidates and estimate savings. Read-only and advisory.list_flow_cards, get_flow_card) returns each card's full argument schema, and full standard and Advanced Flow CRUD (including delete) lets an AI author and tear down the whole cards graph by UUID.