AI agents use set_multiple_annotations 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.
Setting annotations modifies design metadata non-destructively and reversibly. This is a Write operation (creates or modifies data reversibly). Severity is medium because misuse could clutter designs or overwrite important documentation, but the changes are undoable and don't cause data loss or execute arbitrary code.
From the tool's definition Tool description states 'Set multiple annotations parallelly in a node', which is a modification operation. The server description confirms it supports 'annotations' as part of design modification capabilities.
Attacks that exploit this kind of access
Set multiple annotations parallelly in a node. 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_multiple_annotations: 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_multiple_annotations 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_multiple_annotations 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_multiple_annotations. 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_multiple_annotations 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 →