Removes files or directories recursively
AI agents call fs_rmrf to permanently remove resources in Mcp Ssh Tool — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Recursive file/directory removal is inherently irreversible. An AI agent misusing this tool could wipe entire directory trees on a remote system over SSH, with no possibility of recovery unless external backups exist. This is a textbook Destructive operation with critical blast radius.
From the tool's definition 'Removes files or directories recursively' — the name fs_rmrf directly mirrors the Unix `rm -rf` command, which irreversibly deletes files and entire directory trees.
Attacks that exploit this kind of access
Removes files or directories recursively. It is categorised as a Destructive tool in the Mcp Ssh Tool MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Ssh Tool MCP server in PolicyLayer and add a rule for fs_rmrf: 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 Mcp Ssh Tool. Nothing to install.
fs_rmrf 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 fs_rmrf 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 fs_rmrf. 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.
fs_rmrf is provided by the Mcp Ssh Tool MCP server (skot/mcp-ssh-tool). 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 →