Delete a device.
AI agents call delete_device to permanently remove resources in SmartThingsMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a device from a smart home system is an irreversible action that removes the device configuration, automations, and integrations permanently. While not as critical as financial or widespread system destruction, it represents a destructive operation that cannot be undone without manual reconfiguration.
From the tool's definition Tool name is 'delete_device' with description 'Delete a device.' The verb 'delete' indicates irreversible removal of data/state.
Attacks that exploit this kind of access
Delete a device. It is categorised as a Destructive tool in the SmartThingsMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SmartThings MCP server in PolicyLayer and add a rule for delete_device: 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 SmartThingsMCP. Nothing to install.
delete_device is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_device 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 delete_device. 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.
delete_device is provided by the SmartThings MCP server (technohead/smartthings-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 →