Remove a device from a fleet
AI agents call iot_fleet_remove_device to permanently remove resources in Claude Flow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a device from a fleet is a destructive action because it permanently severs the device's registration and fleet membership, which typically cannot be recovered without manual re-provisioning. While not deleting the physical device, the operation irreversibly modifies state in a way that disrupts service continuity.
From the tool's definition Tool name contains 'remove' and description states 'Remove a device from a fleet' — removal of a device from fleet management is an irreversible operation that cannot be easily undone and results in loss of device registration/association.
Attacks that exploit this kind of access
Remove a device from a fleet. It is categorised as a Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow MCP server in PolicyLayer and add a rule for iot_fleet_remove_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 Claude Flow. Nothing to install.
iot_fleet_remove_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 iot_fleet_remove_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 iot_fleet_remove_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.
iot_fleet_remove_device is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.