load_font_async · Claude Talk to Figma MCP: Risk & Policy

WHAT IT DOES

What load_font_async does on Claude Talk to Figma MCP

AI agents invoke load_font_async to trigger actions in Claude Talk to Figma MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why load_font_async needs a policy

Loading a font asynchronously triggers an operation in Figma's runtime environment. It's not a simple read (it changes the state of available fonts) nor a write to design data directly, but an execution of an async operation that modifies the application state. The blast radius is low since it doesn't delete or modify existing design elements.

From the tool's definition 'Load a font asynchronously in Figma' — triggers an external operation (asynchronous font loading) within the Figma environment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_font_async Rate-limited

load_font_async stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "load_font_async": {
      "limits": [
        {
          "counter": "load_font_async_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Talk to Figma MCP, so you can run agents against it safely.

FAQ

Questions about load_font_async

What does the load_font_async tool do? +

Load a font asynchronously in Figma. It is categorised as a Execute tool in the Claude Talk to Figma MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on load_font_async? +

Register the Claude Talk to Figma MCP server in PolicyLayer and add a rule for load_font_async: 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 Claude Talk to Figma MCP. Nothing to install.

What risk level is load_font_async? +

load_font_async is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit load_font_async? +

Yes. Add a rate_limit block to the load_font_async 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.

How do I block load_font_async completely? +

Set action: deny in the PolicyLayer policy for load_font_async. 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.

What MCP server provides load_font_async? +

load_font_async is provided by the Claude Talk to Figma MCP server (stranyer/claude-mcp-figma). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.