Add a scene instance as a child node in another scene
AI agents use instance_scene to create or update resources in Godot MCP Unified — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot MCP Unified environment.
Instancing a scene creates a new node structure within the game's scene tree, which is reversible (the instance can be deleted or undone in the editor). This is a data-creation action typical of Write category.
From the tool's definition Tool name is 'instance_scene' and description states 'Add a scene instance as a child node in another scene' — this is a create/add operation that modifies a scene hierarchy.
Attacks that exploit this kind of access
Add a scene instance as a child node in another scene. It is categorised as a Write tool in the Godot MCP Unified MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot MCP Unified MCP server in PolicyLayer and add a rule for instance_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 Unified. Nothing to install.
instance_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 instance_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 instance_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.
instance_scene is provided by the Godot MCP Unified MCP server (pierrealexandreguillemin-a11y/godot-mcp-unified). 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 →