browser_resize · DevServer MCP: Risk & Policy

WHAT IT DOES

What browser_resize does on DevServer MCP

AI agents invoke browser_resize to trigger actions in DevServer 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 browser_resize needs a policy

Based on the sibling tools, this server provides browser automation via Playwright. 'browser_resize' almost certainly resizes the browser window, which is an Execute-category action (triggering an external browser operation). The description is empty, which lowers confidence, but the context strongly implies a browser viewport/window resize operation.

From the tool's definition Tool name 'browser_resize' on a server with Playwright browser automation tools (browser_click, browser_navigate, browser_type, etc.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_resize Rate-limited

browser_resize 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": {
    "browser_resize": {
      "limits": [
        {
          "counter": "browser_resize_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 DevServer MCP, so you can run agents against it safely.

FAQ

Questions about browser_resize

What does the browser_resize tool do? +

browser_resize. It is categorised as a Execute tool in the DevServer 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 browser_resize? +

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

What risk level is browser_resize? +

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

Can I rate-limit browser_resize? +

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

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

browser_resize is provided by the DevServer MCP server (uninen/devserver-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.