删除目录
AI agents call delete_directory to permanently remove resources in MCP Toolkit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a directory is an irreversible destructive action that cannot be undone. It removes data permanently and has high blast radius if triggered incorrectly by an AI agent (e.g., deleting critical system or application directories). This clearly falls under the Destructive category, which takes precedence over Write due to its permanent nature.
From the tool's definition Tool name is 'delete_directory' and description states '删除目录' (Chinese: 'delete directory'). This irreversibly removes a directory and its contents.
Attacks that exploit this kind of access
删除目录. It is categorised as a Destructive tool in the MCP Toolkit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Toolkit MCP server in PolicyLayer and add a rule for delete_directory: 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 MCP Toolkit. Nothing to install.
delete_directory 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_directory 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_directory. 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_directory is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). 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 →