browser_tab_new · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_tab_new does on Playwright MCP

AI agents invoke browser_tab_new 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_new needs a policy

This tool triggers an external operation (browser tab creation) whose consequences depend on what the agent subsequently does with that tab (navigate to malicious sites, phishing pages, etc.). It is not merely reading data (Read), nor is it permanently destructive (Destructive). It falls under Execute because it invokes a browser operation with side effects that cannot be determined from the tool call alone.

From the tool's definition browser_tab_new opens a new tab, which is a browser control action. The server description states it 'enabling LLMs to interact with web pages' and the sibling tools (browser_click, browser_navigate, browser_drag, etc.) are all browser automation commands…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_tab_new Rate-limited

browser_tab_new 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_new": {
      "limits": [
        {
          "counter": "browser_tab_new_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_new

What does the browser_tab_new tool do? +

Open a new tab. 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_new? +

Register the Playwright MCP server in PolicyLayer and add a rule for browser_tab_new: 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_new? +

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

Can I rate-limit browser_tab_new? +

Yes. Add a rate_limit block to the browser_tab_new 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_new completely? +

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

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