AI agents use reply_to_comment to create or update resources in Figma MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Figma MCP Server environment.
This tool creates new comment replies, which is a reversible modification of data. It does not execute code, delete data, move money, or trigger external side effects beyond adding a comment. Comments and replies can be edited or deleted afterward, making this a Write-category action.
From the tool's definition Tool description states 'Reply to an existing comment' — this creates new comment data (a reply) in Figma, modifying the comment thread. The name and description indicate a write operation that adds content reversibly.
Documented attack patterns abuse exactly the kind of access reply_to_comment gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Figma MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for reply_to_comment:
{
"version": "1",
"default": "deny",
"tools": {
"reply_to_comment": {
"limits": [
{
"counter": "reply_to_comment_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reply_to_comment stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Reply to an existing comment in a Figma file. It is categorised as a Write tool in the Figma MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Figma MCP Server MCP server in PolicyLayer and add a rule for reply_to_comment: 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 MCP Server. Nothing to install.
reply_to_comment 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 reply_to_comment 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 reply_to_comment. 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.
reply_to_comment is provided by the Figma MCP Server MCP server (matthewdailey/figma-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Figma MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Figma MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.