Attach an existing GDScript to a node in a scene
AI agents use attach_script to create or update resources in Godot MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot MCP Server environment.
This is a write operation: it modifies scene structure by attaching a script reference to a node. The change is reversible (the script can be detached or replaced). It does not execute code, delete data, or move money.
From the tool's definition Tool attaches (associates/links) an existing GDScript to a node, modifying the node's script property — a reversible structural change to a scene.
Attacks that exploit this kind of access
Attach an existing GDScript to a node in a scene. It is categorised as a Write tool in the Godot MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot MCP Server MCP server in PolicyLayer and add a rule for attach_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 Server. Nothing to install.
attach_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 attach_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 attach_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.
attach_script is provided by the Godot MCP Server MCP server (koltyakov/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 →