AI agents call get_instance_overrides to retrieve information from MCP Figma without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries override properties from a component instance. It performs no mutation, deletion, or side effects—it only reads and returns data. The mention of applying overrides elsewhere refers to potential use of the returned data by other tools (like those that write modifications), not the action of this tool itself.
From the tool's definition Tool name 'get_instance_overrides' and description 'Get all override properties' indicate retrieval of data about component instance overrides without modification.
Attacks that exploit this kind of access
Get all override properties from a selected component instance. These overrides can be applied to other instances, which will swap them to match the source component. It is categorised as a Read tool in the MCP Figma MCP Server, which means it retrieves data without modifying state.
Register the MCP Figma MCP server in PolicyLayer and add a rule for get_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.
get_instance_overrides is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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 →