# run_test_scenario

Run a multi-step test scenario against the running game

Agent View of the PolicyLayer registry record for `run_test_scenario`. HTML page: https://policylayer.com/tools/keeveeg-godot-mcp/run-test-scenario

## Facts

- Tool: `run_test_scenario`
- Server: Godot (`@keeveeg/godot-mcp`) — https://policylayer.com/tools/keeveeg-godot-mcp.md
- Install: `npx -y @keeveeg/godot-mcp`
- Homepage: https://www.npmjs.com/package/@keeveeg/godot-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `name` | string | no | Scenario name (default: "Unnamed Scenario") |
| `steps` | array | yes | Ordered test steps |

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": "run_test_scenario",
    "arguments": {
      "steps": []
    }
  }
}
```

## Why run_test_scenario is rated High

This tool triggers external operations (multi-step test scenarios) whose effects depend on the test scenario arguments and the current game state. It executes code/logic against a running process, which is characteristic of the Execute category. Severity is high because misconfigured or malicious test scenarios could crash the game, corrupt state, or trigger unintended gameplay behaviors.

From the tool's own definition: "Tool name 'run_test_scenario' combined with description 'Run a multi-step test scenario against the running game' indicates execution of arbitrary test sequences against a live game instance."

## Use case

AI agents invoke run_test_scenario to trigger actions in Godot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## 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": {
    "run_test_scenario": {
      "limits": [
        {
          "counter": "run_test_scenario_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Godot (320)

- `clear_editor_log` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/clear-editor-log.md
- `clear_editor_selection` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/clear-editor-selection.md
- `clear_output` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/clear-output.md
- `delete_export_preset` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-export-preset.md
- `delete_node` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-node.md
- `delete_particles` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-particles.md
- `delete_resource` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-resource.md
- `delete_save_file` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-save-file.md
- `delete_scene` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-scene.md
- `delete_script` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-script.md
- `delete_shader` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-shader.md
- `delete_theme` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/delete-theme.md
- `remove_animation` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-animation.md
- `remove_audio_bus` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-audio-bus.md
- `remove_audio_player` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-audio-player.md
- `remove_autoload` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-autoload.md
- `remove_autoload_config` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-autoload-config.md
- `remove_input_action` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-input-action.md
- `remove_navigation_agent` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-navigation-agent.md
- `remove_navigation_link` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-navigation-link.md
- `remove_navigation_region` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/remove-navigation-region.md
- `reset_editor_layout` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/reset-editor-layout.md
- `tilemap_clear` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/tilemap-clear.md
- `uninstall_addon` — Destructive — https://policylayer.com/tools/keeveeg-godot-mcp/uninstall-addon.md
- `bake_navigation_mesh` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/bake-navigation-mesh.md
- `capture_frames` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/capture-frames.md
- `click_button_by_text` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/click-button-by-text.md
- `continue_execution` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/continue-execution.md
- `evaluate_expression` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/evaluate-expression.md
- `execute_editor_script` — Execute — https://policylayer.com/tools/keeveeg-godot-mcp/execute-editor-script.md
- …and 290 more: https://policylayer.com/tools/keeveeg-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=keeveeg-godot-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/keeveeg-godot-mcp