High Risk →

set_selections

Set selection to multiple nodes in Figma and scroll viewport to show them

How to control set_selections ↓

What set_selections does on Figma AI Bridge

AI agents invoke set_selections to trigger actions in Figma AI Bridge. 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.

High Risk

Why set_selections needs a policy

This tool actively manipulates the Figma application's UI state by changing the current selection and scrolling the viewport. While it doesn't create, modify, or delete design data, it executes operations against an external application that affect its runtime state. It goes beyond a pure read operation since it causes side effects (changed selection state, viewport scroll) in the Figma environment.

From the tool's definition 'Set selection to multiple nodes in Figma and scroll viewport to show them' — triggers a UI state change (selection) and viewport manipulation in an external application (Figma)

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

How to control set_selections

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_selections": {
      "limits": [
        {
          "counter": "set_selections_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

set_selections 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.

  1. Create a free account and register Figma AI Bridge — 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.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about set_selections

What does the set_selections tool do? +

Set selection to multiple nodes in Figma and scroll viewport to show them. It is categorised as a Execute tool in the Figma AI Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on set_selections? +

Register the Figma AI Bridge MCP server in PolicyLayer and add a rule for set_selections: 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 Figma AI Bridge. Nothing to install.

What risk level is set_selections? +

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

Can I rate-limit set_selections? +

Yes. Add a rate_limit block to the set_selections 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_selections completely? +

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

set_selections is provided by the Figma AI Bridge MCP server (renfei-design/figma_ai_bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Figma AI Bridge tool call.

Start from Figma AI Bridge, 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.

64 Figma AI Bridge 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.