Remove a node from a Blueprint graph. Requires the optional C++ plugin.
AI agents call remove_graph_node 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.
Removing a node from a Blueprint graph is a destructive operation. Blueprint nodes may have complex connections and logic; deleting them cannot be automatically undone by the tool itself, and could break Blueprint functionality. This qualifies as Destructive with high severity given the potential to corrupt or break game logic in an Unreal Engine project.
From the tool's definition 'Remove a node from a Blueprint graph' — removal is irreversible without manual undo; deletes graph nodes from a Blueprint.
Attacks that exploit this kind of access
Remove a node from a Blueprint graph. Requires the optional C++ plugin. 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 remove_graph_node: 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.
remove_graph_node 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 remove_graph_node 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 remove_graph_node. 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.
remove_graph_node 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 →