close_tab

THE RISK

Critical Risk

Why close_tab needs a policy

Closing a tab cannot be undone programmatically; any in-progress work, form data, or browser session state in that tab is destroyed. This qualifies as Destructive due to its irreversible nature, though the blast radius is limited to a single browser tab.

From the tool's definition 'Close a browser tab' — closing a tab is irreversible and any unsaved work or state in that tab is permanently lost

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

POLICY

How to control close_tab

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

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "close_tab"
  ]
}

close_tab 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 Webclaw — 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 Webclaw tools

Execute drop_files Drop files onto an element (file input or drag-and-drop target) for uploading Execute hover Hover over an element to trigger mouseover events and reveal hidden UI (e.g., dropdown men Execute invoke_webmcp_tool Invoke a WebMCP tool declared by the current page Execute navigate_to Navigate the browser to a URL Execute new_tab Open a new browser tab Execute wait_for_navigation Wait for the current page to finish loading Execute click Click an element identified by its @ref from the latest page snapshot Execute evaluate Evaluate a JavaScript expression in the page context and return the result.

All 21 Webclaw 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 Webclaw → 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 close_tab

What does the close_tab tool do? +

Close a browser tab. It is categorised as a Destructive tool in the Webclaw 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 close_tab? +

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

What risk level is close_tab? +

close_tab 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 close_tab? +

Yes. Add a rate_limit block to the close_tab 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 close_tab completely? +

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

close_tab is provided by the Webclaw MCP server (kuroko1t/webclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Webclaw tool call.

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

CHECK YOUR STACK →