Delete a model configuration from Open WebUI
AI agents call owui_delete_model to permanently remove resources in ML Lab MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs deletion of model configurations, which cannot be undone. This is a destructive operation as defined by the schema (irreversibly deletes data). The severity is high because deleting ML model configurations could disrupt workflows, cause loss of training metadata, or prevent access to important model definitions.
From the tool's definition Tool name contains 'delete' and description states 'Delete a model configuration from Open WebUI', which is an irreversible operation that removes data.
Attacks that exploit this kind of access
Delete a model configuration from Open WebUI. It is categorised as a Destructive tool in the ML Lab MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ML Lab MCP server in PolicyLayer and add a rule for owui_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 ML Lab MCP. Nothing to install.
owui_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 owui_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 owui_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.
owui_delete_model is provided by the ML Lab MCP server (pushpullcommitpush/ml-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 →