Control covers (blinds, curtains, garage doors). Open, close, stop, or set position.
AI agents invoke cover_control to trigger actions in HomeAssistant 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.
This tool triggers physical actions on real-world devices (blinds, curtains, garage doors). It executes external operations with tangible effects. While the actions are reversible (e.g., you can re-open a closed garage door), it involves operating physical infrastructure. Garage door control in particular has security implications (home access).
From the tool's definition Control covers (blinds, curtains, garage doors). Open, close, stop, or set position.
Documented attack patterns abuse exactly the kind of access cover_control gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HomeAssistant MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for cover_control:
{
"version": "1",
"default": "deny",
"tools": {
"cover_control": {
"limits": [
{
"counter": "cover_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cover_control 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.
Control covers (blinds, curtains, garage doors). Open, close, stop, or set position. It is categorised as a Execute tool in the HomeAssistant MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HomeAssistant MCP server in PolicyLayer and add a rule for cover_control: 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 MCP. Nothing to install.
cover_control 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 cover_control 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 cover_control. 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.
cover_control is provided by the HomeAssistant MCP server (jango-blockchained/advanced-homeassistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from HomeAssistant MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 HomeAssistant MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.