Get historical state changes for entities over time. This endpoint provides access to historical entity state data, which is useful for generating graphs and trends of sensor values, reviewing when devices were turned on/off, and analyzing patterns in system behavior.
AI agents call tools-entities-history 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 historical data about entity state changes without modifying, deleting, executing commands, or initiating financial transactions. It is a passive query mechanism for accessing logged information, analogous to reviewing a system audit log. The low severity reflects that exposing historical state data poses minimal risk compared to tools that control devices or delete data.
From the tool's definition Tool description states it 'Get[s] historical state changes for entities over time' and is 'useful for generating graphs and trends' and 'reviewing when devices were turned on/off' — all read-only query operations with no modification capability.
Attacks that exploit this kind of access
Get historical state changes for entities over time. This endpoint provides access to historical entity state data, which is useful for generating graphs and trends of sensor values, reviewing when devices were turned on/off, and analyzing patterns in system behavior. 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-history: 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-history 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-history 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-history. 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-history 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 →