AI agents use add_track 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 new data (a track) within an existing sequence, which is a reversible modification. It does not execute arbitrary operations, delete data, or move money. The blast radius is medium because misconfiguring tracks could corrupt a sequence project state, but changes are typically undoable in Unreal Engine's undo system.
From the tool's definition Tool name is 'add_track' and description states it will 'Add a track to an actor binding in a sequence' — this creates a new track object within a sequencer binding, modifying the sequence structure.
Attacks that exploit this kind of access
Add a track to an actor binding in a sequence. 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 add_track: 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.
add_track 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 add_track 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 add_track. 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.
add_track 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 →