# create_script

Create a new script from template.

Agent View of the PolicyLayer registry record for `create_script`. HTML page: https://policylayer.com/tools/yanhuifair-godot-mcp/create-script

## Facts

- Tool: `create_script`
- Server: Godot (`@yanhuifair/godot-mcp`) — https://policylayer.com/tools/yanhuifair-godot-mcp.md
- Install: `npx -y @yanhuifair/godot-mcp`
- Homepage: git+https://github.com/yanhuifair/Godot-MCP.git
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 4 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | yes | Output path (relative to project root, e.g. "scripts/enemy.gd") |
| `type` | string | yes | Script language |
| `template` | object | no | Template type |
| `class_name` | object | no | Optional class_name for GDScript |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_script",
    "arguments": {
      "path": "<path>",
      "type": "<type>"
    }
  }
}
```

## Why create_script is rated Medium

Creating a script is a write operation that modifies the project state by adding new code artifacts. While reversible (scripts can be deleted), it has high severity because scripts are executable code that could introduce vulnerabilities, malicious logic, or break the application if an AI agent is tricked into creating harmful code.

From the tool's own definition: "Tool name is 'create_script' and description states 'Create a new script from template.' This action creates a new file (a script) in the Godot project, which is a reversible write operation."

Risk signals: Accepts file system path (path) · Accepts raw HTML/template content (template)

## Use case

AI agents use create_script 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Godot:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_script": {
      "limits": [
        {
          "counter": "create_script_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Godot (281)

- `delete_file` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/delete-file.md
- `editor_delete_asset` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-delete-asset.md
- `editor_delete_selected` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-delete-selected.md
- `editor_remove_autoload` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-remove-autoload.md
- `editor_remove_input_action` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-remove-input-action.md
- `editor_remove_node` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-remove-node.md
- `remove_animation_track` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-animation-track.md
- `remove_audio_bus` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-audio-bus.md
- `remove_autoload` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-autoload.md
- `remove_input_action` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-input-action.md
- `remove_node` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-node.md
- `remove_shader_graph_node` — Destructive — https://policylayer.com/tools/yanhuifair-godot-mcp/remove-shader-graph-node.md
- `compile_shader` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/compile-shader.md
- `editor_bake_lightmaps` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-bake-lightmaps.md
- `editor_bake_navigation` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-bake-navigation.md
- `editor_debug_break` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-debug-break.md
- `editor_debug_continue` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-debug-continue.md
- `editor_debug_step` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-debug-step.md
- `editor_debug_step_over` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-debug-step-over.md
- `editor_enable_plugin` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-enable-plugin.md
- `editor_evaluate_expression` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-evaluate-expression.md
- `editor_focus` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-focus.md
- `editor_get_class_doc` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-get-class-doc.md
- `editor_open_asset` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-open-asset.md
- `editor_open_dock` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-open-dock.md
- `editor_play` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-play.md
- `editor_reimport_asset` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-reimport-asset.md
- `editor_reload_scene` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-reload-scene.md
- `editor_run_gdscript` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-run-gdscript.md
- `editor_run_specific_scene` — Execute — https://policylayer.com/tools/yanhuifair-godot-mcp/editor-run-specific-scene.md
- …and 251 more: https://policylayer.com/tools/yanhuifair-godot-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=yanhuifair-godot-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/yanhuifair-godot-mcp