Delete a model.
AI agents call model_delete to permanently remove resources in Kaggle-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is an irreversible operation that cannot be undone without external recovery mechanisms. This qualifies as Destructive rather than Write. While the blast radius depends on which model is targeted, deletion of a user's trained model or shared model could cause significant loss of work and intellectual property.
From the tool's definition Tool name is 'model_delete' with description 'Delete a model.' The verb 'delete' combined with the action on a model resource indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a model. It is categorised as a Destructive tool in the Kaggle-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kaggle- MCP server in PolicyLayer and add a rule for model_delete: 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 Kaggle-MCP. Nothing to install.
model_delete 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 model_delete 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 model_delete. 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.
model_delete is provided by the Kaggle- MCP server (realbytecode/kaggle-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 →