browser_focus · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_focus does on Browser

AI agents invoke browser_focus 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_focus needs a policy

Focusing an element is a browser action that triggers external UI operations and can activate event listeners (focus/blur events), potentially influencing form behavior or other side effects. It falls under Execute as it performs a programmatic browser interaction rather than merely reading data or writing persistent data.

From the tool's definition 'Focus an element' — triggers a browser interaction (focusing a DOM element) via Playwright automation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_focus Rate-limited

browser_focus 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_focus": {
      "limits": [
        {
          "counter": "browser_focus_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_focus

What does the browser_focus tool do? +

Focus an element (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_focus? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_focus: 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_focus? +

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

Can I rate-limit browser_focus? +

Yes. Add a rate_limit block to the browser_focus 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_focus completely? +

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

browser_focus 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.