Récupère l
AI agents call get_entity_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 a Home Assistant entity. There are no side effects, no data modification, no code execution, and no destructive or financial operations. Reading smart home device states is a low-severity information disclosure risk—exposure enables monitoring but not control.
From the tool's definition Tool name is 'get_entity_state'; prefix 'get_' and verb 'retrieve' (implied by French 'Récupère') indicate a read-only query operation. Description is incomplete ('Récupère l') but the name strongly suggests state retrieval without modification.
Attacks that exploit this kind of access
Récupère l. 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_entity_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_entity_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_entity_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_entity_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_entity_state is provided by the Home Assistant MCP Server MCP server (jonathan97480/mcphomeassistant). 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 →