container_add_child
Instance a Control-derived child under a Container node (VBoxContainer, GridContainer, MarginContainer, …) so it participates in the container's layout (undoable). Refuses a non-Container parent or a non-Control child. Returns the new node's path.
This record as markdown: /tools/breakpoint-mcp/container-add-child.md
What container_add_child does on Breakpoint
AI agents use container_add_child 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 | — | Node name (defaults to the class name) |
type | string | Yes | Control subclass to instance as the container's child, e.g. Button, Label |
container_path | string | Yes | Container node path relative to the scene root |
Parameters from the server's own tool schema.
Why container_add_child is rated Medium
This tool creates/instantiates new UI nodes within a scene hierarchy. It is a Write operation because it creates data structures (scene nodes) that can be reversed via undo. The blast radius is medium—improper instantiation could clutter the scene tree or create unexpected UI layouts, but the undoable nature and containment within a UI framework limits severity.
From the tool's definition Tool creates a new child node under a Container: "Instance a Control-derived child under a Container node", "Returns the new node's path". The operation is explicitly marked as "undoable", confirming it modifies the scene tree reversibly.
Attacks that exploit this kind of access
The rule that runs container_add_child 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 container_add_child, this is the rule to start with:
container_add_child 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 container_add_child call is checked against it from then on.
Questions about container_add_child
Instance a Control-derived child under a Container node (VBoxContainer, GridContainer, MarginContainer, …) so it participates in the container's layout (undoable). Refuses a non-Container parent or a non-Control child. Returns the new node's path. 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.
container_add_child accepts 3 parameters: name, type, container_path. Required: type, container_path. 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 container_add_child: 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.
container_add_child 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 container_add_child 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 container_add_child. 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.
container_add_child 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