Re-layout the canvas as a hierarchical directed graph. Rectangles become nodes, arrows become edges, and positions are recomputed so the diagram reads in the chosen direction (TB = top-to-bottom, default; LR = left-to-right). Bound labels (containerId) move with their rectangles. Elements that ar...
AI agents use canvas_auto_layout to create or update resources in Whiteboard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Whiteboard environment.
This tool modifies the positions of existing canvas elements by recomputing their layout. It changes data (element positions) on the canvas in a reversible way — no elements are deleted, just repositioned. This fits the Write category. Severity is medium because misuse could scramble a complex diagram's layout, but no data is permanently destroyed.
From the tool's definition Re-layout the canvas as a hierarchical directed graph... positions are recomputed so the diagram reads in the chosen direction
Attacks that exploit this kind of access
Re-layout the canvas as a hierarchical directed graph. Rectangles become nodes, arrows become edges, and positions are recomputed so the diagram reads in the chosen direction (TB = top-to-bottom, default; LR = left-to-right). Bound labels (containerId) move with their rectangles. Elements that are not rectangles or that are disconnected land in layer 0. It is categorised as a Write tool in the Whiteboard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Whiteboard MCP server in PolicyLayer and add a rule for canvas_auto_layout: 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 Whiteboard. Nothing to install.
canvas_auto_layout 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 canvas_auto_layout 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 canvas_auto_layout. 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.
canvas_auto_layout is provided by the Whiteboard MCP server (kamiazya/whiteboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →