Comment threads not yet marked resolved in Figma.
AI agents call get_unresolved_comments to retrieve information from Figma Comments without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation on Figma comments. It retrieves information about unresolved comment threads for review or triage purposes, but does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal—an agent could exfiltrate comment content but cannot damage or alter Figma files or comments themselves.
From the tool's definition Tool retrieves comment threads marked as 'not yet resolved' from Figma—a pure data retrieval operation with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Comment threads not yet marked resolved in Figma. It is categorised as a Read tool in the Figma Comments MCP Server, which means it retrieves data without modifying state.
Register the Figma Comments MCP server in PolicyLayer and add a rule for get_unresolved_comments: 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 Figma Comments. Nothing to install.
get_unresolved_comments 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_unresolved_comments 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_unresolved_comments. 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_unresolved_comments is provided by the Figma Comments MCP server (processedfood/figma-comments-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 →