AI agents invoke recompile_material to trigger actions in Unreal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Recompiling a material triggers an execution process (shader compilation) in Unreal Engine. It doesn't simply read or write data in a reversible way; it runs the material compiler pipeline. The blast radius is medium since a failed or corrupted recompile could break material rendering across the project, but it doesn't irreversibly delete data.
From the tool's definition 'Recompile a material after making changes to its graph' — triggers a compilation/build process on a material asset
Attacks that exploit this kind of access
Recompile a material after making changes to its graph. It is categorised as a Execute tool in the Unreal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unreal MCP server in PolicyLayer and add a rule for recompile_material: 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.
recompile_material is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the recompile_material 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 recompile_material. 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.
recompile_material 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 →