删除存储桶
AI agents call delete_bucket to permanently remove resources in MinIO Storage MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a bucket from MinIO storage without reversal. Once executed, the bucket and potentially all objects within it are lost. This is a destructive operation that cannot be undone through normal means, placing it in the Destructive category. Severity is high because deleting a bucket can cause significant data loss, though the impact depends on what the bucket contains.
From the tool's definition Tool name 'delete_bucket' with description '删除存储桶' (Chinese: 'delete bucket'). The name and function directly indicate irreversible deletion of a bucket and all its contents.
Attacks that exploit this kind of access
删除存储桶. It is categorised as a Destructive tool in the MinIO Storage MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MinIO Storage MCP server in PolicyLayer and add a rule for delete_bucket: 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 MinIO Storage MCP. Nothing to install.
delete_bucket 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_bucket 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_bucket. 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_bucket is provided by the MinIO Storage MCP server (pickstar-2002/minio-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 →