Delete an asset. Checks for references first.
AI agents call delete_asset to permanently remove resources in Unreal — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes assets from an Unreal Engine project, which cannot be undone. While it includes a reference check (a safeguard), the core operation is destructive—it irreversibly deletes data. In the context of an AI agent with access to this tool, misuse could result in permanent loss of critical project assets, models, textures, or blueprints.
From the tool's definition Tool name 'delete_asset' combined with description 'Delete an asset' explicitly indicates permanent removal of assets. The phrase 'Checks for references first' confirms this is a deletion operation with safety checks, but deletion is irreversible.
Attacks that exploit this kind of access
Delete an asset. Checks for references first. It is categorised as a Destructive tool in the Unreal MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Unreal MCP server in PolicyLayer and add a rule for delete_asset: 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 Unreal. Nothing to install.
delete_asset 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_asset 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_asset. 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_asset is provided by the Unreal MCP server (sam-david/unreal-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 →