Delete a file or folder on Fastmail Files (WebDAV).
AI agents call files_delete to permanently remove resources in Pyfastmail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of files or folders is an irreversible operation that cannot be undone by the AI agent. The blast radius is significant because mistaken or malicious deletion of user files represents permanent data loss.
From the tool's definition Tool name and description explicitly state 'Delete a file or folder' — direct destructive action on user data storage without reversibility. The tool operates on Fastmail Files (WebDAV), a persistent file storage system.
Attacks that exploit this kind of access
Delete a file or folder on Fastmail Files (WebDAV). It is categorised as a Destructive tool in the Pyfastmail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for files_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 Pyfastmail. Nothing to install.
files_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 files_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 files_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.
files_delete is provided by the Pyfastmail MCP server (pjosols/pyfastmail-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 →