删除OSS存储桶
AI agents call delete_oss_bucket to permanently remove resources in Alibaba Cloud Operations MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes an OSS (Object Storage Service) bucket, which is an irreversible destructive operation. Deleting a bucket can result in permanent loss of all stored objects within it, making this a critical-severity destructive action with no inherent undo mechanism.
From the tool's definition Tool name: 'delete_oss_bucket'; description: '删除OSS存储桶' (meaning 'Delete OSS bucket')
Attacks that exploit this kind of access
删除OSS存储桶. It is categorised as a Destructive tool in the Alibaba Cloud Operations MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Alibaba Cloud Operations MCP Server MCP server in PolicyLayer and add a rule for delete_oss_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 Alibaba Cloud Operations MCP Server. Nothing to install.
delete_oss_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_oss_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_oss_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_oss_bucket is provided by the Alibaba Cloud Operations MCP Server MCP server (radiumgu/alicloud-ops-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 →