批量删除坚果云中的文件/目录（逗号分隔多个路径）
AI agents call batch_delete to permanently remove resources in Nutstore — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of files or directories is irreversible and cannot be undone. The batch nature of this tool increases the blast radius—a single errant call could delete multiple critical files or entire directory trees. This is the most severe category applicable. Destructive category takes precedence over Write or Execute.
From the tool's definition Tool name is 'batch_delete' and description states '批量删除坚果云中的文件/目录' which translates to 'batch delete files/directories in Nutstore cloud storage'. The description explicitly indicates deletion of files and directories via comma-separated paths.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
批量删除坚果云中的文件/目录（逗号分隔多个路径）. It is categorised as a Destructive tool in the Nutstore MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nutstore MCP server in PolicyLayer and add a rule for batch_delete: 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 Nutstore. Nothing to install.
batch_delete 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 batch_delete 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 batch_delete. 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.
batch_delete is provided by the Nutstore MCP server (silverze/nutstore-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 →