Safely delete a file with confirmation.
AI agents call delete_file to permanently remove resources in Claude File Management Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
File deletion is a destructive operation that permanently removes data without the ability to recover it through the tool itself. While the description mentions 'confirmation' as a safety measure, this does not change the destructive nature of the action.
From the tool's definition Tool name 'delete_file' and description 'Safely delete a file with confirmation' indicate irreversible deletion of data. The operation cannot be undone—once a file is deleted, it is permanently removed from the filesystem.
Attacks that exploit this kind of access
Safely delete a file with confirmation. It is categorised as a Destructive tool in the Claude File Management Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude File Management Server MCP server in PolicyLayer and add a rule for delete_file: 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 Claude File Management Server. Nothing to install.
delete_file 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_file 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_file. 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_file is provided by the Claude File Management Server MCP server (vipin1000/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 →