browser_wait_for_selector · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_wait_for_selector does on Browser

AI agents invoke browser_wait_for_selector to trigger actions in Browser. 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_wait_for_selector needs a policy

browser_wait_for_selector is a control flow tool that pauses execution until a DOM element appears. While waiting itself is passive, it's part of a browser automation workflow designed to interact with external web services and trigger consequential actions. An AI agent could use this to wait for confirmation dialogs, payment forms, or other critical UI elements before performing subsequent actions.

From the tool's definition Tool enables programmatic control via Playwright to wait for page elements, which is part of browser automation that can trigger external operations and side effects depending on what follows the wait condition.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_wait_for_selector Rate-limited

browser_wait_for_selector 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_wait_for_selector": {
      "limits": [
        {
          "counter": "browser_wait_for_selector_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 Browser, so you can run agents against it safely.

FAQ

Questions about browser_wait_for_selector

What does the browser_wait_for_selector tool do? +

Wait for an element to appear on the page (see browser_docs). It is categorised as a Execute tool in the Browser 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_wait_for_selector? +

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

What risk level is browser_wait_for_selector? +

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

Can I rate-limit browser_wait_for_selector? +

Yes. Add a rate_limit block to the browser_wait_for_selector 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_wait_for_selector completely? +

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

browser_wait_for_selector is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.