Medium Risk

set_selection_colors

Recursively change all stroke and fill colors of a node and all its descendants. Works like Figma

How to control set_selection_colors ↓

What set_selection_colors does on Claude Talk to Figma MCP

AI agents use set_selection_colors 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.

Medium Risk

Why set_selection_colors needs a policy

This tool modifies design attributes (colors) within a Figma document in a reversible manner. While it affects multiple nodes recursively, the changes are non-destructive and can be undone. This is a Write operation rather than Destructive because color changes can be reverted.

From the tool's definition Tool description states 'Recursively change all stroke and fill colors of a node and all its descendants', indicating modification of visual properties.

Documented attack patterns abuse exactly the kind of access set_selection_colors gives an agent:

How to control set_selection_colors

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Talk to Figma MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for set_selection_colors:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_selection_colors": {
      "limits": [
        {
          "counter": "set_selection_colors_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

set_selection_colors 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.

  1. Create a free account and register Claude Talk to Figma MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about set_selection_colors

What does the set_selection_colors tool do? +

Recursively change all stroke and fill colors of a node and all its descendants. Works like 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 set_selection_colors? +

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

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

Can I rate-limit set_selection_colors? +

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

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

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

Enforce policy on every Claude Talk to Figma MCP tool call.

Start from Claude Talk to Figma MCP, 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.

93 Claude Talk to Figma MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.