create_text · Claude Talk to Figma MCP: Risk & Policy

WHAT IT DOES

What create_text does on Claude Talk to Figma MCP

AI agents use create_text to create or update resources in Claude Talk to Figma MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Talk to Figma MCP environment.

WHY IT NEEDS A POLICY

Why create_text needs a policy

This tool creates (writes) a new text element in Figma, which is a reversible modification of design data. It does not execute arbitrary code, delete content, or move financial resources. The severity is medium because misuse could clutter or deface a design project, but the changes can be undone through Figma's standard undo/delete features, and the blast radius is limited to a single design document.

From the tool's definition Tool name is 'create_text' and description states 'Create a new text element in Figma' — this is a creation operation that adds new content to a design document.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_text Rate-limited

create_text 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_text": {
      "limits": [
        {
          "counter": "create_text_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 create_text

What does the create_text tool do? +

Create a new text element in Figma. It is categorised as a Write tool in the Claude Talk to Figma MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_text? +

Register the Claude Talk to Figma MCP server in PolicyLayer and add a rule for create_text: 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 create_text? +

create_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_text? +

Yes. Add a rate_limit block to the create_text 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 create_text completely? +

Set action: deny in the PolicyLayer policy for create_text. 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 create_text? +

create_text 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.