dropCollection
AI agents call dropCollection 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 term 'drop' in database contexts universally refers to permanent, irreversible deletion of data structures. Even without description details, this naming pattern maps clearly to the Destructive category. If misused by an AI agent, it could permanently remove entire collections of data.
From the tool's definition Tool name 'dropCollection' uses 'drop' which conventionally means irreversible deletion of a database collection. The empty description prevents verification of exact behavior, but the naming convention strongly indicates a destructive operation.
Attacks that exploit this kind of access
dropCollection. 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 dropCollection: 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.
dropCollection 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 dropCollection 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 dropCollection. 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.
dropCollection 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.