Mcp Hass
CheckedProvides MCP tools guidance and assistance for orchestrating AI agents and multi-step workflows.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add aahl/skills --skill mcp-hass -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
aahl
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Only contacts known or declared hosts: homeassistant.local.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
homeassistant.locallocalNo obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned aahl/skills at 47edd621df.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 47edd621df
- Manifest
- skills/mcp-hass/SKILL.md
- Scanned
- 1 file, 52 lines
About this skill
What it does
This skill allows AI agents to interact with Home Assistant, a popular home automation platform. It enables agents to retrieve sensor data (like temperature or humidity), control devices (turning lights on/off), and execute automations within the Home Assistant environment. The agent can respond to natural language requests related to your smart home setup.
When to use it
- Smart Home Control: Allow a user to verbally adjust thermostat settings, turn off lights in a specific room, or lock doors.
- Status Monitoring: Have an agent report the current temperature of a room, check if a door is locked, or provide other real-time sensor data from your home.
- Automation Triggering: Enable users to trigger existing Home Assistant automations via voice commands (e.g., "Run my bedtime scene").
- Home Status Summaries: Request an overview of the current state of your smart home, including device statuses and recent events.
Key capabilities
- Retrieval of sensor data from Home Assistant.
- Control of devices connected to Home Assistant.
- Execution of existing Home Assistant automations.
- Natural language understanding for smart home requests.
Example prompts
- "What's the temperature in the living room?"
- "Turn off the kitchen lights."
- "Run my 'Good Night' automation."
Tips & gotchas
- Requires a functional Home Assistant installation and proper configuration of the skill with your Home Assistant instance.
- The agent’s ability to understand commands depends on how your devices and automations are named in Home Assistant; clear, descriptive names will improve accuracy.