Get the current state of all (or specific) Home Assistant entities. This endpoint provides a complete snapshot of the current state of your home automation system, including all entities (devices, sensors, automations, etc.) and their attributes. Returns the current state value, all attributes, a...
AI agents call tools-entities-states 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 retrieves and queries the current state of smart home entities (devices, sensors, automations) without any side effects or data modifications. It is a read-only operation that gathers information about the system state.
From the tool's definition Tool name and description indicate it 'Get[s] the current state' and 'provides a complete snapshot' of Home Assistant entities without modifying them. The description explicitly states it 'Returns' state information only.
Attacks that exploit this kind of access
Get the current state of all (or specific) Home Assistant entities. This endpoint provides a complete snapshot of the current state of your home automation system, including all entities (devices, sensors, automations, etc.) and their attributes. Returns the current state value, all attributes, and last changed/updated timestamps. 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 tools-entities-states: 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.
tools-entities-states 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 tools-entities-states 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 tools-entities-states. 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.
tools-entities-states is provided by the Home Assistant MCP Server MCP server (oleander/home-assistant-mcp-server). 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 →