AI agents use connect_material_expressions 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.
The tool modifies the material expression graph by establishing connections between nodes, which is a Write operation—creating/modifying data structures. While this can affect rendering output, the changes are reversible (connections can be unwired) and do not constitute Destructive operations.
From the tool's definition Tool name 'connect_material_expressions' and description 'Wire two material expression nodes together' indicate modification of material node graphs in Unreal Engine. This is a reversible graph editing operation that creates connections between nodes.
Attacks that exploit this kind of access
Wire two material expression nodes together. 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 connect_material_expressions: 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.
connect_material_expressions 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 connect_material_expressions 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 connect_material_expressions. 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.
connect_material_expressions 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 →