browser_close

THE RISK

Critical Risk

Why browser_close needs a policy

Closing a browser session cannot be undone; all runtime state (open tabs, session data, in-memory content) is destroyed. While artifacts are saved, the active session itself is irreversibly terminated. This qualifies as Destructive rather than Execute because the primary effect is irreversible termination of a resource.

From the tool's definition 'Closes browser and saves all artifacts' — closing the browser is an irreversible termination of the browser session; any unsaved state, open pages, or in-progress operations are permanently lost.

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

POLICY

How to control browser_close

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

policy.json

{
  "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.

Create a free account and register Browser-Debugger — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Browser-Debugger tools

Execute browser_launch 🔴 ALWAYS USE THIS FIRST - Starts browser automation. Execute media_record_video Video recording control. action: 'start' or 'stop'. Execute app_interact Universal form filler and button clicker. fields: list of values, button: button text hint Execute viewport_set_mode Changes viewport. mode: 'iphone', 'ipad', or 'desktop'. Read performance_get_metrics Analyzes page performance (Core Web Vitals: LCP, FCP, CLS). Read debug_read_logs Reads console and network logs (last 20 each). Read dom_get_source Returns HTML source of current page (truncated to 5000 chars). Read dom_inspect_element Inspects element visibility, position, and attributes. Use selector OR xpath.

All 14 Browser-Debugger tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Browser-Debugger → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browser_close

What does the browser_close tool do? +

Closes browser and saves all artifacts (video, logs, screenshots, HAR, trace). It is categorised as a Destructive tool in the Browser-Debugger 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_close? +

Register the Browser-Debugger 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 Browser-Debugger. Nothing to install.

What risk level is browser_close? +

browser_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_close? +

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.

How do I block browser_close completely? +

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.

What MCP server provides browser_close? +

browser_close is provided by the Browser-Debugger MCP server (selvadinesh-giga/mcp-based-browser-debug-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Browser-Debugger tool call.

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

CHECK YOUR STACK →