script_create

A write tool on the Godot MCP server.

SERVERGodot SOURCEchanceflow/godot-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/chanceflow-godot-mcp/script-create.md

WHAT IT DOES

What script_create does on Godot

AI agents use script_create to create or update resources in Godot, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot environment.

RISK

Why script_create is rated Medium

Script creation in a game engine modifies project files and can introduce code that affects game behavior. This is a Write operation (reversible, creates new artifacts) rather than Execute (which would run code immediately). However, the lack of a description and the AI agent context elevates severity to 'high' because a malicious agent could inject arbitrary code into game scripts.

From the tool's definition Tool name 'script_create' indicates creation of a new script artifact in the Godot engine context. The server description confirms it enables interaction with Godot including scene management and project manipulation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs script_create safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Godot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For script_create, this is the rule to start with:

script_create Rate-limited

script_create stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "script_create": {
      "limits": [
        {
          "counter": "script_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Godot, apply this rule, and every script_create call is checked against it from then on.

FAQ

Questions about script_create

What does the script_create tool do? +

script_create is a write tool on the Godot MCP server. It is categorised as a Write tool in the Godot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on script_create? +

Register the Godot MCP server in PolicyLayer and add a rule for script_create: 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. Nothing to install.

What risk level is script_create? +

script_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit script_create? +

Yes. Add a rate_limit block to the script_create 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.

How do I block script_create completely? +

Set action: deny in the PolicyLayer policy for script_create. 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.

What MCP server provides script_create? +

script_create is provided by the Godot MCP server (chanceflow/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Godot, and thousands of servers like it.

This server

All 84 Godot tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →