browser_tab_select · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_tab_select does on Playwright MCP

AI agents invoke browser_tab_select to trigger actions in Playwright 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_tab_select needs a policy

Selecting a tab is a browser action that changes the active browser context. While it doesn't directly modify data, it is an execution-level browser operation that controls which page the agent interacts with next, potentially enabling further high-impact actions. In the context of a Playwright automation server, tab selection is an external browser operation with side effects on the automation session state.

From the tool's definition 'Select a tab by index' — switches browser context to a specific tab, triggering navigation state changes and enabling subsequent interactions with that tab's content

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_tab_select Rate-limited

browser_tab_select 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_tab_select": {
      "limits": [
        {
          "counter": "browser_tab_select_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 Playwright MCP, so you can run agents against it safely.

FAQ

Questions about browser_tab_select

What does the browser_tab_select tool do? +

Select a tab by index. It is categorised as a Execute tool in the Playwright 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_tab_select? +

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

What risk level is browser_tab_select? +

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

Can I rate-limit browser_tab_select? +

Yes. Add a rate_limit block to the browser_tab_select 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_tab_select completely? +

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

browser_tab_select is provided by the Playwright MCP server (lewisvoncken/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.