AI agents invoke entity_action to trigger actions in Hass-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name 'entity_action' strongly implies triggering actions on smart home entities (e.g., turning on/off lights, locks, alarms, thermostats). Given the server's stated purpose of controlling smart home entities, this is likely an Execute-category tool with high severity due to potential physical-world consequences (unlocking doors, disabling alarms, etc.).
From the tool's definition Tool name 'entity_action' on a Home Assistant MCP server that 'control[s] smart home entities, and perform[s] automation tasks'
Documented attack patterns abuse exactly the kind of access entity_action 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 entity_action:
{
"version": "1",
"default": "deny",
"tools": {
"entity_action": {
"limits": [
{
"counter": "entity_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}entity_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
entity_action. It is categorised as a Execute tool in the Hass-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hass- MCP server in PolicyLayer and add a rule for entity_action: 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.
entity_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the entity_action 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 entity_action. 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.
entity_action 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.