AI agents use generate_ui 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 based on user input. While it modifies the design file by adding UI components, these changes are reversible (elements can be deleted via the delete_node sibling tool). It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool description states it "creates corresponding Figma elements" in response to text input, and sibling tools include create_frame, create_rectangle, create_text which are Write operations. The verb "Generate" and "creates" indicate reversible data creation.
Attacks that exploit this kind of access
Generate a UI design from a text description. Parses the prompt for common UI patterns (header, hero, cards, form, footer) and creates corresponding Figma elements. 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 generate_ui: 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.
generate_ui 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 generate_ui 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 generate_ui. 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.
generate_ui 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 →