AI agents use create_scene to create or update resources in Godot MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot MCP environment.
Creating a new scene file is a reversible write operation. It modifies the project by adding a new asset file but does not execute code, delete data, or cause irreversible changes. The severity is medium because creating arbitrary scenes could potentially corrupt project structure or consume resources if abused, but the operation is easily reversible (the file can be deleted).
From the tool's definition Tool description states 'Create a new Godot scene file' — this is a creation operation that writes new data to the filesystem.
Attacks that exploit this kind of access
Create a new Godot scene file. It is categorised as a Write tool in the Godot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot MCP server in PolicyLayer and add a rule for create_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 Godot MCP. Nothing to install.
create_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 create_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 create_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.
create_scene is provided by the Godot MCP server (jamesdowzard/godot-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 →