AI agents call search_entities_tool to retrieve information from Hass-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to query or filter entities in Home Assistant, which is a non-destructive read operation. It would retrieve information about available devices or automation entities, comparable to the 'get_entities_by_area' sibling tool. Even if an AI misused this tool, the blast radius would be minimal—searching entities has no side effects on smart home state or data.
From the tool's definition Tool name contains 'search_entities' which suggests querying or retrieving entities from Home Assistant. The sibling tools indicate a pattern where tools with 'get_' and 'search_' prefixes perform read operations (e.g., get_entities_by_area, get_entity,…
Documented attack patterns abuse exactly the kind of access search_entities_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hass-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_entities_tool:
{
"version": "1",
"default": "deny",
"tools": {
"search_entities_tool": {}
}
}search_entities_tool is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_entities_tool. It is categorised as a Read tool in the Hass-MCP MCP Server, which means it retrieves data without modifying state.
Register the Hass- MCP server in PolicyLayer and add a rule for search_entities_tool: 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 Hass-MCP. Nothing to install.
search_entities_tool 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 search_entities_tool 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 search_entities_tool. 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.
search_entities_tool is provided by the Hass- MCP server (voska/hass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Hass-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Hass-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.