MCP server
by oleander
Transform your smarter home with Home Assistant: advanced home automation smart home control and secure device managemen
Connects Large Language Models to Home Assistant, enabling natural language control and querying of smart home devices and automations.
Home Assistant is a community-built MCP server published by oleander that provides AI assistants with tools and capabilities via the Model Context Protocol. Transform your smarter home with Home Assistant: advanced home automation smart home control and secure device managemen It is categorized under developer tools.
You can install Home Assistant in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Home Assistant is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Useful MCP listing: Home Assistant is the kind of server we cite when onboarding engineers to host + tool permissions.
I recommend Home Assistant for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Home Assistant has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, Home Assistant benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Strong directory entry: Home Assistant surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Home Assistant is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Home Assistant is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired Home Assistant into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Useful MCP listing: Home Assistant is the kind of server we cite when onboarding engineers to host + tool permissions.
I recommend Home Assistant for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
showing 1-10 of 55
A Model Context Protocol (MCP) server for integrating with Home Assistant, allowing LLMs to control and query your smart home.
# Install globally using bun
bun install -g home-assistant-mcp-server
# Or install from source
git clone https://github.com/oleander/home-assistant-mcp-server.git
cd home-assistant-mcp-server
bun install
bun run build
bun link
Create a .env file in your current directory with the following variables:
# Required configurations
HASS_URL=http://your-home-assistant:8123 # URL to your Home Assistant instance
HASS_TOKEN=your_long_lived_access_token # Long-lived access token for authentication
# Optional configurations
PORT=3000 # Port for the HTTP server (default: 3000)
HASS_MOCK=false # Enable mock data mode when Home Assistant is unavailable (default: false)
| Variable | Required | Default | Description |
|---|---|---|---|
HASS_URL | Yes | - | URL to your Home Assistant instance (e.g., http://homeassistant.local:8123) |
HASS_TOKEN | Yes | - | Long-lived access token for authenticating with Home Assistant |
PORT | No | 3000 | Port number for the HTTP server when using HTTP/SSE transport |
HASS_MOCK | No | false | When set to "true", enables mock data mode for testing without a Home Assistant connection |
To get a long-lived access token:
# Standard mode (requires a running Home Assistant instance)
home-assistant-mcp-server # Start with HTTP/SSE transport
home-assistant-mcp-server --stdio # Start with stdio transport for direct process communication
# Demo mode (with mock data when Home Assistant is unavailable)
home-assistant-mcp-server --mock # Start with HTTP/SSE transport and mock data
home-assistant-mcp-server --stdio --mock # Start with stdio transport and mock data
To use with Claude Desktop:
Edit your Claude Desktop config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonAdd the server configuration:
{
"mcpServers": {
"homeassistant": {
"command": "home-assistant-mcp-server"
"env": {
"HASS_URL": "http://your-home-assistant:8123",
"HASS_TOKEN": "your_token_here",
"HASS_MOCK": "true"
}
}
}
}
If you have Home Assistant running, simply remove the --mock flag and set HASS_MOCK to false.
The server exposes several tools for interacting with Home Assistant:
states - Query entity stateslights - List lightslight - Control a lightservice - Call Home Assistant serviceshistory - Retrieve historical entity dataservices - List available servicesconfig - Get Home Assistant configurationdomains - List available domainserror_log - Get Home Assistant error logdevices - Get all devices in Home AssistantFor detailed usage examples, see docs/hass-mcp.md.
This server requires a Home Assistant access token with full access. Consider these security recommendations:
.env file secure and don't commit it to source controlThis project is licensed under the MIT License - see the LICENSE file for details.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.