// SCAN REPORT

Figma MCP Server

31 tools. 7 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

7 can modify or destroy data

24 read-only

31 tools total

Community server · catalogue entry verified 12/06/2026 · full schemas captured for 30 of 31 tools

How to control Figma MCP Server ↓

TOOL MAP

What Figma MCP Server exposes to your agents

Read (24) Write / Execute (4) Destructive / Financial (3)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Figma MCP Server costs in tokens

2,712 tokens of tool definitions, loaded on every request

1.4% of a 200k context window

288 heaviest tool: figma_get_images

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Figma MCP Server tools

Destructive · High figma_delete_comment The tool permanently removes a comment, which cannot be undone. Destructive · Medium figma_delete_comment_reaction The tool performs an irreversible deletion of a comment reaction. Destructive · High figma_delete_webhook This tool permanently removes a webhook configuration, which cannot be undone. Write · Low figma_post_comment Posting a comment creates new data within Figma but does not modify existing design content, delete anything, execute code, or impact financial systems.

7 of Figma MCP Server's 31 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 MCP Server

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

Deny destructive operations

{
  "figma_delete_comment": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "figma_post_comment": {
    "limits": [
      {
        "counter": "figma_post_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "figma_get_comment_reactions": {
    "limits": [
      {
        "counter": "figma_get_comment_reactions_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 MCP Server — 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 →

Instant setup, no code required.

FULL CATALOGUE

All 31 Figma MCP Server tools

DESTRUCTIVE 3 tools

Destructive figma_delete_comment Delete a comment from a Figma file Destructive figma_delete_comment_reaction Delete a reaction from a comment Destructive figma_delete_webhook Delete a webhook

WRITE 4 tools

Write figma_post_comment Add a comment to a Figma file Write figma_post_comment_reaction Add a reaction to a comment Write figma_post_webhook Create a webhook Write figma_update_webhook Update a webhook

READ 24 tools

Read figma_get_comment_reactions Get reactions for a comment Read figma_get_comments Get comments in a Figma file Read figma_get_component Get a component by key Read figma_get_component_set Get a component set by key Read figma_get_file Get a Figma file by key Read figma_get_file_component_sets Get component sets in a file Read figma_get_file_components Get components in a file Read figma_get_file_nodes Get specific nodes from a Figma file Read figma_get_file_styles Get styles in a file Read figma_get_file_versions Get version history of a Figma file Read figma_get_image_fills Get image fills in a Figma file Read figma_get_images Render images from a Figma file Read figma_get_library_analytics_component_usages Get library analytics component usage data Read figma_get_library_analytics_style_usages Get library analytics style usage data Read figma_get_library_analytics_variable_usages Get library analytics variable usage data Read figma_get_me Get the current user Read figma_get_project_files Get files in a project Read figma_get_style Get a style by key Read figma_get_team_component_sets Get component sets in a team Read figma_get_team_components Get components in a team Read figma_get_team_projects Get projects in a team Read figma_get_team_styles Get styles in a team Read figma_get_team_webhooks Get webhooks for a team Read figma_get_webhook Get a webhook by ID

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Figma MCP Server

Can an AI agent delete data through the Figma MCP Server MCP server? +

Yes. The Figma MCP Server server exposes 3 destructive tools including figma_delete_comment, figma_delete_comment_reaction, figma_delete_webhook. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Figma MCP Server? +

The Figma MCP Server server has 4 write tools including figma_post_comment, figma_post_comment_reaction, figma_post_webhook. 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 MCP Server.

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

31 tools across 3 categories: Destructive, Read, Write. 24 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Figma MCP Server? +

Register the Figma MCP Server 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 MCP Server tool call.

Deterministic rules across all 31 Figma MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FIGMA →

Instant setup, no code required.

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