delete_image_set
AI agents call delete_image_set to permanently remove resources in Amazon SageMaker AI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'delete_image_set' tool performs an irreversible action (deletion) on SageMaker image sets, which are data artifacts. Even without a description, the delete verb clearly maps to the Destructive category. In a SageMaker context, image sets can be expensive ML training datasets or model artifacts; unauthorized deletion could halt pipelines or cause data loss.
From the tool's definition Tool name 'delete_image_set' indicates irreversible deletion operation. Description is empty, but the verb 'delete' is unambiguous—it removes data that cannot be recovered.
Attacks that exploit this kind of access
delete_image_set. It is categorised as a Destructive tool in the Amazon SageMaker AI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for delete_image_set: 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 Amazon SageMaker AI MCP Server. Nothing to install.
delete_image_set 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_image_set 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_image_set. 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_image_set is provided by the Amazon SageMaker AI MCP Server MCP server (awslabs.sagemaker-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.