ha-mcp
Verified Safeby homeassistant-ai
Overview
A Model Context Protocol (MCP) server that provides AI agents with comprehensive control and monitoring capabilities for Home Assistant through REST API and WebSocket integration, offering over 20 enhanced tools for smart home management and automation.
Installation
ha-mcp webEnvironment Variables
- HOMEASSISTANT_URL
- HOMEASSISTANT_TOKEN
- LOG_LEVEL
- MCP_API_KEY
- MCP_WEB_SECRET
- FUZZY_THRESHOLD
- BACKUP_HINT
- HAMCP_ENABLE_CUSTOM_COMPONENT_INTEGRATION
Security Notes
The server's security is largely dependent on the underlying Home Assistant instance it connects to and the validity of the provided long-lived access token. The application logic generally delegates complex operations (like template evaluation) to Home Assistant's internal APIs, relying on HA's inherent sandboxing. File system interactions, such as those related to the 'ha_mcp_tools' custom component, include explicit path validation against allowed directories, demonstrating a conscious effort to limit potential access. The 'ha_install_mcp_tools' tool, which handles HACS component installation, is disabled by default behind a feature flag and targets a specific hardcoded repository, preventing arbitrary code injection through user input. Proper management of Home Assistant itself, including strong API token security, is crucial.
Similar Servers
advanced-homeassistant-mcp
A Model Context Protocol (MCP) server that enables AI assistants (like Claude, GPT, Cursor) to seamlessly interact with Home Assistant, allowing control of smart home devices through natural language commands.
openhab-mcp
This project provides an MCP (Model Context Protocol) server to enable AI assistants like Claude and Cline to interact with and manage a real openHAB smart home system via its REST API.
mqtt-mcp
Connects LLM agents to MQTT devices for AI-driven automation in IoT, smart home, and industrial control systems.
mcp
The MCP Server provides an AI-powered framework for command execution, plugin-based tools, secure Python evaluation, and knowledge management, designed for standalone or embedded use.