Delete a model instance.
AI agents call model_instance_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 of model instances cannot be undone and results in permanent loss of the model artifact. This is a destructive operation affecting user data. While not as critical as account deletion, it represents irreversible data loss within the user's workspace.
From the tool's definition Tool name is 'model_instance_delete' with description 'Delete a model instance.' The verb 'delete' combined with 'instance' indicates irreversible removal of a stored model artifact on Kaggle.
Attacks that exploit this kind of access
Delete a model instance. 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_instance_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_instance_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_instance_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_instance_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_instance_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 →