Get the current state and attributes of any Home Assistant entity
AI agents call get_state to retrieve information from Home Assistant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current state of smart home entities without modifying, deleting, or executing any actions. It is purely informational, matching the Read category definition (retrieves or queries data; no side effects). The severity is low because unauthorized state queries pose minimal risk—they reveal device status but do not control devices or affect system integrity.
From the tool's definition Tool name 'get_state' and description 'Get the current state and attributes of any Home Assistant entity' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the current state and attributes of any Home Assistant entity. It is categorised as a Read tool in the Home Assistant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Home Assistant MCP Server MCP server in PolicyLayer and add a rule for get_state: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Home Assistant MCP Server. Nothing to install.
get_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_state rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_state. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_state is provided by the Home Assistant MCP Server MCP server (mjrestivo16/mcp-homeassistant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →