AI agents invoke load_scene to trigger actions in Unity MCP. 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.
Loading a scene is an active operation that changes the Unity Editor's runtime state, unloading the current scene and loading a new one. This is not a simple read; it executes a scene transition that can discard unsaved changes and alter the editor environment. It falls under Execute due to its side effects on the running editor state.
From the tool's definition 'Load a scene by name or index' and 'switching between scenes' — actively triggers a scene transition in the Unity Editor, changing application state
Attacks that exploit this kind of access
Load a scene by name or index. Useful for switching between scenes in your project. It is categorised as a Execute tool in the Unity MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unity MCP server in PolicyLayer and add a rule for load_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.
load_scene 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 load_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 load_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.
load_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 →