// SCAN REPORT

Figma Comments

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 02/07/2026

How to control Figma Comments ↓

TOOL MAP

What Figma Comments exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Figma Comments tools

Write · Medium reply_to_comment This tool creates new data (comment replies) in a reversible manner.

1 of Figma Comments's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Figma Comments

PolicyLayer is an MCP gateway — it sits between your AI agents and Figma Comments, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "reply_to_comment": {
    "limits": [
      {
        "counter": "reply_to_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_all_comments": {
    "limits": [
      {
        "counter": "get_all_comments_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Figma Comments — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON FIGMA COMMENTS →

Instant setup, no code required.

FULL CATALOGUE

All 5 Figma Comments tools

WRITE 1 tools

Write reply_to_comment Post a reply to an existing comment thread in a Figma file. Use a thread id from the [brackets] in fetch outpu

READ 4 tools

Read get_all_comments Fetch every comment thread in a Figma file, grouped by page and the canvas element each thread is pinned to. R Read get_comments_mentioning_me Comment threads where the owner of the Figma token is @mentioned. Read get_recent_comments Comment threads with activity in the past N hours (default 24). Read get_unresolved_comments Comment threads not yet marked resolved in Figma.

FAQ

Questions about Figma Comments

How do I prevent bulk modifications through Figma Comments? +

The Figma Comments server has 1 write tools including reply_to_comment. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Figma Comments.

How many tools does the Figma Comments MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Figma Comments? +

Register the Figma Comments MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Figma Comments tool call.

Deterministic rules across all 5 Figma Comments tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FIGMA COMMENTS →

Instant setup, no code required.

5 Figma Comments tools catalogued and risk-classified — across an index of 43,000+ MCP servers.