Critical Risk →

browser_tab_close

Close a tab

How to control browser_tab_close ↓

What browser_tab_close does on Playwright MCP

AI agents call browser_tab_close to permanently remove resources in Playwright MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why browser_tab_close needs a policy

Closing a tab cannot be undone; any unsaved form data, navigation history, or active session within that tab is permanently lost. This maps to Destructive. Severity is medium because the blast radius is limited to a single browser tab rather than persistent data stores.

From the tool's definition 'Close a tab' — closing a browser tab is an irreversible action that destroys the tab's state, session, and any unsaved data within it.

Documented attack patterns abuse exactly the kind of access browser_tab_close gives an agent:

How to control browser_tab_close

PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_tab_close:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "browser_tab_close"
  ]
}

browser_tab_close disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Playwright MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about browser_tab_close

What does the browser_tab_close tool do? +

Close a tab. It is categorised as a Destructive tool in the Playwright MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on browser_tab_close? +

Register the Playwright MCP server in PolicyLayer and add a rule for browser_tab_close: 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_close? +

browser_tab_close is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit browser_tab_close? +

Yes. Add a rate_limit block to the browser_tab_close 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_close completely? +

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

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

Enforce policy on every Playwright MCP tool call.

Start from Playwright MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

32 Playwright MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.