AI agents use create_rectangle 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 creates new design elements in Figma, which is a reversible write operation. It does not execute arbitrary code, delete assets, or create financial obligations. The blast radius is minimal—a misused tool would only add unwanted design elements that can be easily undone. Severity is low because Figma designs are typically non-critical assets and the action is fully reversible.
From the tool's definition Tool name 'create_rectangle' and description stating 'Create a rectangle shape in Figma' with customizable properties (fills, rounded corners) indicates data creation/modification.
Attacks that exploit this kind of access
Create a rectangle shape in Figma. Can have fills and rounded corners. 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 create_rectangle: 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.
create_rectangle 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 create_rectangle 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 create_rectangle. 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.
create_rectangle 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 →