MCP Hass Agent Skill
The skill for control Home Assistant smart home devices and query states using MCP protocol.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/aahl/skills --skill mcp-hassThe instruction itself
5 sections, as written by the authorHome Assistant
Control Home Assistant smart home and query states using MCP protocol.
Prerequisites
Enable MCP server in Home Assistant:
- Browse to your Home Assistant instance.
- Go to Settings > Devices & services.
- In the bottom right corner, select the + Add Integration button.
- From the list, select Model Context Protocol.
- Follow the instructions on screen to complete the setup.
Config
When prompted that the MCP server does not exist, remind the user to configure the HASS_BASE_URL and HASS_ACCESS_TOKEN environment variables by executing the following command to add the configuration:
npx -y mcporter config add home-assistant \
--transport http \
--url "${HASS_BASE_URL:-http://homeassistant.local:8123}/api/mcp" \
--header "Authorization=Bearer \${HASS_ACCESS_TOKEN}"
Usage
# Get states
npx -y mcporter call home-assistant.GetLiveContext
# Turn on the device
npx -y mcporter call home-assistant.HassTurnOn(name: "Bedroom Light")
npx -y mcporter call home-assistant.HassTurnOn(name: "Light", area: "Bedroom")
# Turn off the device
npx -y mcporter call home-assistant.HassTurnOff(name: "Bedroom Light")
npx -y mcporter call home-assistant.HassTurnOff(area: "Bedroom", domain: ["light"])
# Control light
# brightness: The percentage of the light, where 0 is off and 100 is fully lit.
# color: Name of color
npx -y mcporter call home-assistant.HassLightSet(name: "Bedroom Light", brightness: 50)
# Control fan
# percentage: The percentage of the fan, where 0 is off and 100 is full speed.
npx -y mcporter call home-assistant.HassFanSetSpeed(name: "Fan", area: "Bedroom", percentage: 80)
Execute the following command to learn about specific usage methods:
npx -y mcporter list home-assistant --schema --all-parameters
About mcporter
- To improve compatibility, use
npx -y mcporterinstead ofmcporterwhen executing commands. - https://github.com/steipete/mcporter/raw/refs/heads/main/docs/call-syntax.md
- https://github.com/steipete/mcporter/raw/refs/heads/main/docs/cli-reference.md
Other skills for the same job
different authors, same section of the catalogue
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
How to use it
Take aahl/mcp-hass from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.