AI agents use generate_collision 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 creates or modifies collision geometry for static meshes in Unreal Engine, which is a reversible change to asset properties. It does not execute arbitrary code, delete data, or move funds. While it could impact game performance or behavior if misapplied, the effect is reversible through regeneration or removal of collision data.
From the tool's definition Tool name 'generate_collision' and description 'Generate collision for a static mesh' indicates creation/modification of collision data for game assets. This is a write operation that modifies mesh properties.
Attacks that exploit this kind of access
Generate collision for a static mesh. 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 generate_collision: 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.
generate_collision 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 generate_collision 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 generate_collision. 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.
generate_collision 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 →