viewport_set · Whiteboard MCP: Risk & Policy

WHAT IT DOES

What viewport_set does on Whiteboard

AI agents invoke viewport_set to trigger actions in Whiteboard. 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 viewport_set needs a policy

This tool triggers a browser action (panning/zooming the canvas viewport), which constitutes an external operation affecting the browser's display state. It does not read, write persistent data, or destroy anything, but it does execute a UI-level action in the browser. Severity is low since misuse only affects the visual viewport with no data loss or financial impact.

From the tool's definition Pan/zoom the browser canvas to focus attention

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

viewport_set Rate-limited

viewport_set 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": {
    "viewport_set": {
      "limits": [
        {
          "counter": "viewport_set_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 Whiteboard, so you can run agents against it safely.

FAQ

Questions about viewport_set

What does the viewport_set tool do? +

Pan/zoom the browser canvas to focus attention. Use mode=. It is categorised as a Execute tool in the Whiteboard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on viewport_set? +

Register the Whiteboard MCP server in PolicyLayer and add a rule for viewport_set: 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 Whiteboard. Nothing to install.

What risk level is viewport_set? +

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

Can I rate-limit viewport_set? +

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

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

viewport_set is provided by the Whiteboard MCP server (kamiazya/whiteboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.