Permanently delete a collection. This cannot be undone.
AI agents call romm_delete_collection to permanently remove resources in Mcp Romm — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (a collection and likely all its contents). Destructive category applies to actions that cannot be undone. High severity reflects the permanent loss of user data that would result from accidental or malicious invocation by an AI agent.
From the tool's definition Tool description states: "Permanently delete a collection. This cannot be undone." The word "Permanently" combined with "cannot be undone" indicates irreversible data deletion.
Attacks that exploit this kind of access
Permanently delete a collection. This cannot be undone. It is categorised as a Destructive tool in the Mcp Romm MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Romm MCP server in PolicyLayer and add a rule for romm_delete_collection: 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 Romm. Nothing to install.
romm_delete_collection 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 romm_delete_collection 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 romm_delete_collection. 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.
romm_delete_collection is provided by the Mcp Romm MCP server (lodordev/mcp-romm). 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 →