control_create
Instance a Control-derived UI node (Button, Label, Panel, VBoxContainer, TextureRect, …) under a parent (undoable). Refuses non-Control classes. Optional 'text' is applied only to controls that expose a 'text' property. Returns the new node's path.
This record as markdown: /tools/breakpoint-mcp/control-create.md
What control_create does on Breakpoint
AI agents use control_create 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) |
text | string | — | Initial text; applied only if the control has a 'text' property |
type | string | Yes | Control subclass to instance, e.g. Button, Label, Panel, VBoxContainer, TextureRect |
parent_path | string | Yes | Parent node path relative to the scene root; "." for the root |
Parameters from the server's own tool schema.
Why control_create is rated Medium
This tool creates new UI elements (Control-derived nodes like Button, Label, Panel, etc.) in a UI tree structure. While creation is a form of modification, the key distinguishing factor is that the description explicitly marks the action as 'undoable'—meaning it can be reversed and is not irreversible. This makes it a Write operation rather than Destructive.
From the tool's definition The tool 'control_create' creates a new UI node under a parent and returns the path, with the description stating it is 'undoable', meaning the action is reversible. This is a creation operation that modifies the UI hierarchy.
Attacks that exploit this kind of access
The rule that runs control_create 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 control_create, this is the rule to start with:
control_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every control_create call is checked against it from then on.
Questions about control_create
Instance a Control-derived UI node (Button, Label, Panel, VBoxContainer, TextureRect, …) under a parent (undoable). Refuses non-Control classes. Optional 'text' is applied only to controls that expose a 'text' property. 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.
control_create accepts 4 parameters: name, text, type, parent_path. Required: type, parent_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 control_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 Breakpoint. Nothing to install.
control_create 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 control_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.
Set action: deny in the PolicyLayer policy for control_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.
control_create 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