AI agents call delete_items to permanently remove resources in Filesystem — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of files or directories cannot be undone and results in permanent data loss. This is the most severe category applicable. The tool operates on a local filesystem (notes system) and could remove multiple items at once, creating significant blast radius if an AI agent misuses it by deleting unintended files or critical directories.
From the tool's definition Tool name is "delete_items" and description states "Delete multiple specified files or directories." The verb "delete" combined with the irreversible nature of file/directory deletion clearly indicates this is a destructive operation.
Documented attack patterns abuse exactly the kind of access delete_items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Filesystem, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_items:
{
"version": "1",
"default": "deny",
"hide": [
"delete_items"
]
}delete_items disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete multiple specified files or directories. It is categorised as a Destructive tool in the Filesystem MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Filesystem MCP server in PolicyLayer and add a rule for delete_items: 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 Filesystem. Nothing to install.
delete_items 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_items 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_items. 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_items is provided by the Filesystem MCP server (sylphxai/filesystem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Filesystem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Filesystem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.