history_query
AI agents call history_query to retrieve information from Homeassistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'history_query' strongly implies querying or retrieving historical records (sensor readings, event logs, state changes) from Home Assistant, which is a read-only operation with no side effects. Although the description is empty, the naming convention and context of a home automation system support this classification. Blast radius is low since querying history cannot change system state or trigger actions.
From the tool's definition Tool name 'history_query' suggests retrieval of historical data from Home Assistant without modification. Sibling tools like 'calendar_access', 'api_info', and 'config_check' are similarly read-only operations.
Attacks that exploit this kind of access
history_query. It is categorised as a Read tool in the Homeassistant MCP Server, which means it retrieves data without modifying state.
Register the Homeassistant MCP server in PolicyLayer and add a rule for history_query: 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 Homeassistant. Nothing to install.
history_query 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 history_query 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 history_query. 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.
history_query is provided by the Homeassistant MCP server (robbrad/homeassistant-mcp). 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 →