AI agents use set_material_instance_vector 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.
This tool modifies material instance parameters, which is a reversible write operation. The change can be undone by setting the parameter to a different value. While it affects visual rendering in Unreal Engine, the modification is not destructive and can be easily reverted.
From the tool's definition Tool name is 'set_material_instance_vector' and description states 'Set a vector parameter on a material instance.' The verb 'set' indicates modification of an existing resource (a material instance parameter) in a reversible manner.
Attacks that exploit this kind of access
Set a vector parameter on a material instance. 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 set_material_instance_vector: 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.
set_material_instance_vector 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 set_material_instance_vector 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 set_material_instance_vector. 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.
set_material_instance_vector 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 →