AI agents use set_instance_overrides to create or update resources in MCP Figma — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Figma environment.
The tool creates or modifies design data within Figma by applying overrides to component instances and swapping components. These are Write-category operations because they alter existing design elements.
From the tool's definition 'Apply previously copied overrides to selected component instances. Target instances will be swapped to the source component and all copied override properties will be applied.' - This tool modifies component instances by applying overrides and swapping…
Attacks that exploit this kind of access
Apply previously copied overrides to selected component instances. Target instances will be swapped to the source component and all copied override properties will be applied. It is categorised as a Write tool in the MCP Figma MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Figma MCP server in PolicyLayer and add a rule for set_instance_overrides: 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 MCP Figma. Nothing to install.
set_instance_overrides 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_instance_overrides 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_instance_overrides. 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_instance_overrides is provided by the MCP Figma MCP server (yelowflash09/figma_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 →