AI agents use create_component_instance 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.
This tool falls under Write because it creates and adds a new component instance to a Figma design, which is a reversible modification. It is not Destructive (no deletion/irreversible changes), not Execute (no arbitrary code execution), not Read (it modifies rather than retrieves), and not Financial.
From the tool's definition create_component_instance explicitly creates a new component instance in Figma, modifying the design by adding a new element. The tool name uses 'create', indicating a write operation that adds data to the design file.
Attacks that exploit this kind of access
Create an instance of a component in Figma. 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 create_component_instance: 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.
create_component_instance 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_component_instance 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_component_instance. 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_component_instance 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 →