Detach a GDScript from a node in a scene (.tscn file)
AI agents use detach_script 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.
This tool modifies scene configuration by detaching scripts from nodes, which changes the node's behavior and the scene file structure. The modification is reversible (a script can be re-attached), so it falls under Write rather than Destructive.
From the tool's definition detach_script: Detach a GDScript from a node in a scene (.tscn file) - modifies scene structure by removing script associations from nodes
Attacks that exploit this kind of access
Detach a GDScript from a node in a scene (.tscn file). 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 detach_script: 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.
detach_script 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 detach_script 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 detach_script. 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.
detach_script 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 →