AI agents call browser_close to permanently remove resources in Better Playwright MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a page cannot be undone; any unsaved form data, in-memory state, or ongoing interactions are permanently lost. This qualifies as Destructive. Severity is medium because the blast radius is limited to the current browser session rather than external data stores.
From the tool's definition 'Close the page' — terminates the browser page, which is an irreversible action that destroys the current page state, any unsaved data, and the browsing session.
Documented attack patterns abuse exactly the kind of access browser_close gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Better Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_close:
{
"version": "1",
"default": "deny",
"hide": [
"browser_close"
]
}browser_close disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Close the page. It is categorised as a Destructive tool in the Better Playwright MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Better Playwright MCP server in PolicyLayer and add a rule for browser_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 Better Playwright MCP. Nothing to install.
browser_close is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the browser_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.
Set action: deny in the PolicyLayer policy for browser_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.
browser_close is provided by the Better Playwright MCP server (livoras/better-playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Better 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.
29 Better Playwright MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.