Remove a filesystem path from allowed_roots.
AI agents call remove_allowed_root to permanently remove resources in Unlimited — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing an allowed root irreversibly revokes access permissions for that filesystem path. This is a configuration deletion that cannot be easily undone and could block agents from accessing critical paths, disrupting operations. It is a destructive configuration change rather than a simple data modification.
From the tool's definition Remove a filesystem path from allowed_roots
Attacks that exploit this kind of access
Remove a filesystem path from allowed_roots. It is categorised as a Destructive tool in the Unlimited MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Unlimited MCP server in PolicyLayer and add a rule for remove_allowed_root: 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 Unlimited. Nothing to install.
remove_allowed_root 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 remove_allowed_root 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 remove_allowed_root. 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.
remove_allowed_root is provided by the Unlimited MCP server (triumsebas/unlimited-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
remove_allowed_root is one line of Unlimited's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →