AI agents use create_blueprint to create or update resources in Unreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unreal environment.
Creating a Blueprint class is a Write operation because it creates new data (a Blueprint asset) that can be modified or deleted later. It has moderate blast radius in that it could clutter the project with unwanted assets or interfere with development workflows, but the operation is reversible and doesn't execute arbitrary code or delete existing content.
From the tool's definition Tool name 'create_blueprint' and description 'Create a new Blueprint class' indicate creation of a new asset/class in Unreal Engine. This is a reversible modification operation.
Attacks that exploit this kind of access
Create a new Blueprint class. It is categorised as a Write tool in the Unreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unreal MCP server in PolicyLayer and add a rule for create_blueprint: 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.
create_blueprint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_blueprint 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 create_blueprint. 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.
create_blueprint 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 →