Deletes a GameObject by name.
AI agents call delete_object to permanently remove resources in MCP For Unity — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes GameObjects from a Unity project. Deletion cannot be undone programmatically through the MCP interface, making it a destructive operation. The severity is high because an AI agent could accidentally or maliciously delete critical game objects, scenes, or prefabs, causing loss of work. The confidence is high because the description unambiguously indicates deletion.
From the tool's definition Tool name is 'delete_object' and description states it 'Deletes a GameObject by name.' The verb 'deletes' is explicitly destructive.
Attacks that exploit this kind of access
Deletes a GameObject by name. It is categorised as a Destructive tool in the MCP For Unity MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP For Unity MCP server in PolicyLayer and add a rule for delete_object: 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 MCP For Unity. Nothing to install.
delete_object 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_object 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_object. 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_object is provided by the MCP For Unity MCP server (yunuscan/mcpforunity). 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 →