UMG Widget Blueprints, Editor Utility Widgets, and Editor Utility Blueprints. Actions: - read_tree: Read widget hierarchy. Params: assetPath - get_details: Inspect widget. Params: assetPath, widgetName - set_property: Set widget property. Params: assetPath, widgetName, propertyName, value - list:...
Risk signalsAccepts file system path (directory) · High parameter count (22 properties) · Admin/system-level operation
Part of the Ue server.
Free to start. No card required.
AI agents may call widget to permanently remove or destroy resources in Ue. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call widget in a loop, permanently destroying resources in Ue. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"widget"
]
}See the full Ue policy for all 22 tools.
These attack patterns abuse exactly the kind of access widget gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
UMG Widget Blueprints, Editor Utility Widgets, and Editor Utility Blueprints. Actions: - read_tree: Read widget hierarchy. Params: assetPath - get_details: Inspect widget. Params: assetPath, widgetName - set_property: Set widget property. Params: assetPath, widgetName, propertyName, value - list: List Widget BPs. Params: directory?, recursive? - read_animations: Read UMG animations. Params: assetPath - create: Create Widget BP. Params: name, packagePath?, parentClass? - create_utility_widget: Create editor utility widget. Params: name, packagePath? - run_utility_widget: Open editor utility widget. Params: assetPath - create_utility_blueprint: Create editor utility blueprint. Params: name, packagePath? - run_utility_blueprint: Run editor utility blueprint. Params: assetPath - add_widget: Add widget to widget tree. Params: assetPath, widgetClass, widgetName?, parentWidgetName? - remove_widget: Remove widget from tree. Params: assetPath, widgetName - move_widget: Reparent widget. Params: assetPath, widgetName, newParentWidgetName - set_root: Replace WBP root with an existing widget by name (#365). Params: assetPath, widgetName - wrap_root: Wrap the current root in a new panel widget (UMG 'Wrap With'). Params: assetPath, wrapperClass (must be a UPanelWidget subclass), wrapperName? (#365) - list_classes: List available widget classes - list_runtime: (#160) List live UUserWidget instances in the PIE world. Params: classFilter?, namePrefix?, viewportOnly? - get_runtime: (#160) Inspect a live PIE widget tree with text/visibility/brush/percent values. Params: widgetName? | className?, childName?, maxDepth? - get_runtime_delegates: (#161) Read delegate binding state on a live PIE widget. Params: widgetName, className?. Returns array of {delegateName, isBound, numBindings}. It is categorised as a Destructive tool in the Ue MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ue MCP server in PolicyLayer and add a rule for widget: 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 Ue. Nothing to install.
widget 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 widget 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 widget. 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.
widget is provided by the Ue MCP server (ue-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Ue tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.