Delete a directory from the remote server.
AI agents call ftp_rmdir to permanently remove resources in Ftp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Directory deletion is inherently destructive—it cannot be undone and removes data with no recovery path. This is a high-severity operation because it can recursively eliminate multiple files and subdirectories in a single action, and misuse by an AI agent could result in significant data loss.
From the tool's definition Tool name 'ftp_rmdir' and description 'Delete a directory from the remote server' explicitly indicate irreversible deletion of directory structures and their contents.
Attacks that exploit this kind of access
Delete a directory from the remote server. It is categorised as a Destructive tool in the Ftp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ftp MCP server in PolicyLayer and add a rule for ftp_rmdir: 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 Ftp. Nothing to install.
ftp_rmdir 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 ftp_rmdir 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 ftp_rmdir. 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.
ftp_rmdir is provided by the Ftp MCP server (kynlos/ftp-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 →