Create or update an annotation
AI agents use set_annotation to create or update resources in Cursor Talk to Figma MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cursor Talk to Figma MCP environment.
This tool modifies annotations within Figma designs but does not delete data (which would be Destructive) or execute arbitrary code (which would be Execute). Annotations are metadata or notes attached to design elements, and their creation or modification is reversible—users can edit or remove them later.
From the tool's definition The tool is described as 'Create or update an annotation', which indicates it performs reversible modifications to Figma design data. The verbs 'create' and 'update' are characteristic of Write operations.
Attacks that exploit this kind of access
Create or update an annotation. It is categorised as a Write tool in the Cursor Talk to Figma MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cursor Talk to Figma MCP server in PolicyLayer and add a rule for set_annotation: 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 Cursor Talk to Figma MCP. Nothing to install.
set_annotation 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_annotation 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_annotation. 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_annotation is provided by the Cursor Talk to Figma MCP server (paragdesai1/parag-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 →