Permanently delete a single file from the filesystem.
AI agents call deleteFile to permanently remove resources in Shell MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data from the filesystem with no recovery mechanism. While the blast radius depends on which files an agent targets, the capability to permanently delete files represents a destructive action that justifies the Destructive category and high severity. Confidence is high because the description unambiguously describes permanent deletion.
From the tool's definition Tool name is 'deleteFile' and description states 'Permanently delete a single file from the filesystem.' The use of 'permanently delete' indicates an irreversible operation that cannot be undone.
Attacks that exploit this kind of access
Permanently delete a single file from the filesystem. It is categorised as a Destructive tool in the Shell MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Shell MCP server in PolicyLayer and add a rule for deleteFile: 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 Shell MCP. Nothing to install.
deleteFile 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 deleteFile 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 deleteFile. 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.
deleteFile is provided by the Shell MCP server (lucivuc/shell-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 →