AI agents use apply_auto_layout to create or update resources in Figmad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Figmad environment.
This tool modifies design structure by applying auto-layout properties to frames, which changes how child elements are positioned and spaced. This is a reversible modification (auto-layout can be removed or reconfigured), making it a Write operation rather than Destructive.
From the tool's definition Tool applies auto-layout configuration to a frame, which modifies the layout properties and arrangement of design elements. The description states it 'automatically arranges children' - a structural modification to the design.
Attacks that exploit this kind of access
Apply auto-layout to a frame. Auto-layout automatically arranges children horizontally or vertically with consistent spacing. It is categorised as a Write tool in the Figmad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Figmad MCP server in PolicyLayer and add a rule for apply_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 Figmad. Nothing to install.
apply_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 apply_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 apply_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.
apply_auto_layout is provided by the Figmad MCP server (toro1221/figmad-mcp). 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 →