Delete a model
AI agents call delete_model to permanently remove resources in Rockfish MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a model is a destructive operation that permanently removes a trained machine learning artifact. This cannot be reversed without retraining, representing significant loss of computational work and potential business impact. While not financial, it is more severe than Write (which is reversible) and falls clearly into the Destructive category.
From the tool's definition Tool name: 'delete_model'; description: 'Delete a model'. The verb 'delete' explicitly indicates irreversible removal of data (a trained ML model), which cannot be undone.
Attacks that exploit this kind of access
Delete a model. It is categorised as a Destructive tool in the Rockfish MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for delete_model: 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 Rockfish MCP Server. Nothing to install.
delete_model 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 delete_model 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 delete_model. 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.
delete_model is provided by the Rockfish MCP Server MCP server (wolfdancer/rockfish-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 →