scene_new
Create a new scene with the given root class, save it to a path, and open it. DESTRUCTIVE (writes a file) — gated by confirmation.
This record as markdown: /tools/breakpoint-mcp/scene-new.md
What scene_new does on Breakpoint
AI agents use scene_new to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Root node name (defaults to the class name) |
path | string | Yes | Where to save, e.g. res://scenes/new.tscn |
confirm | boolean | — | Skip the confirmation prompt (auto-approve) |
overwrite | boolean | — | Replace if it exists |
root_type | string | Yes | Root node class, e.g. Node2D, Node3D, Control |
Parameters from the server's own tool schema.
Why scene_new is rated Medium
This tool creates and saves a new scene file. Although the description uses the word 'DESTRUCTIVE', the action is creating/writing a new file rather than deleting or irreversibly overwriting existing data. It is gated by confirmation, reducing risk. The primary effect is a reversible file write (the file can be deleted afterward). Severity is medium due to potential to overwrite an existing file at the given path.
From the tool's definition Create a new scene with the given root class, save it to a path, and open it. DESTRUCTIVE (writes a file) — gated by confirmation.
Risk signalsAccepts file system path (path) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs scene_new safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scene_new, this is the rule to start with:
scene_new 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every scene_new call is checked against it from then on.
Questions about scene_new
Create a new scene with the given root class, save it to a path, and open it. DESTRUCTIVE (writes a file) — gated by confirmation. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
scene_new accepts 5 parameters: name, path, confirm, overwrite, root_type. Required: path, root_type. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for scene_new: 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 Breakpoint. Nothing to install.
scene_new 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 scene_new 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 scene_new. 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.
scene_new is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue