删除 TOS 存储桶
AI agents call tos_delete_bucket to permanently remove resources in TOS MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a storage bucket is a destructive operation that cannot be undone and results in permanent loss of all data within that bucket. This is irreversible and has significant blast radius if triggered by an AI agent without proper authorization. While not involving financial transactions, the data loss severity justifies 'high' classification as a destructive action.
From the tool's definition Tool name 'tos_delete_bucket' and description '删除 TOS 存储桶' (Delete TOS storage bucket) directly indicates irreversible deletion of an entire bucket and all its contents.
Attacks that exploit this kind of access
删除 TOS 存储桶. It is categorised as a Destructive tool in the TOS MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TOS MCP Server MCP server in PolicyLayer and add a rule for tos_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 TOS MCP Server. Nothing to install.
tos_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 tos_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 tos_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.
tos_delete_bucket is provided by the TOS MCP Server MCP server (jneless/tos-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 →