AI agents use set_fills 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 or modifies design data (fill properties) within Figma in a reversible manner. It does not delete or destroy data (would be Destructive), does not execute arbitrary code (would be Execute), and does not move money (would be Financial). The modification is recoverable through undo or subsequent set_fills calls, fitting the Write category.
From the tool's definition "Set fill colors/gradients on a node. Replaces all existing fills." – the tool modifies visual properties of design elements by replacing existing fills, which is a reversible mutation of design data.
Attacks that exploit this kind of access
Set fill colors/gradients on a node. Replaces all existing fills. 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 set_fills: 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.
set_fills 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 set_fills 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 set_fills. 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.
set_fills 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 →