删除存储桶中的对象
AI agents call delete_object 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 objects from MinIO storage with no undo capability. While the blast radius is limited to a single object at a time (unlike delete_bucket or delete_objects which affect multiple items), it is still a destructive operation. Severity is 'high' rather than 'critical' because impact is typically scoped to one object unless called in a loop.
From the tool's definition Tool name 'delete_object' and description '删除存储桶中的对象' (delete object from storage bucket) indicates irreversible deletion of data from object storage.
Attacks that exploit this kind of access
删除存储桶中的对象. 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_object: 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_object 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_object 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_object. 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_object 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 →