AI agents use save_scene to create or update resources in Unity MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unity MCP environment.
This tool modifies scene files on disk, which is reversible through undo/version control systems. It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read data (Read). The severity is medium because while scene modifications can affect project integrity, they are recoverable and don't have catastrophic real-world impact like financial or security breaches.
From the tool's definition Tool name 'save_scene' and description 'Save the current scene or all open scenes' indicates creation or modification of persistent data (scene files).
Attacks that exploit this kind of access
Save the current scene or all open scenes. Essential for preserving changes made during automation. It is categorised as a Write tool in the Unity MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unity MCP server in PolicyLayer and add a rule for save_scene: 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 Unity MCP. Nothing to install.
save_scene 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 save_scene 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 save_scene. 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.
save_scene is provided by the Unity MCP server (muammar-yacoob/unity-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 →