browser_close

THE RISK

Critical Risk

Why browser_close needs a policy

Killing all Chrome processes is an irreversible termination action — any unsaved state, open tabs, or in-progress operations are permanently lost. While contained within a sandbox, it forcibly destroys running processes without recovery, making it Destructive rather than Execute.

From the tool's definition Kill all Chrome processes inside the sandbox

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 Taw Computer, 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 Taw Computer — 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 Taw Computer tools

Destructive vm_destroy Destroy a sandbox and free its ports. By default the VM filesystem is saved as a snapshot Destructive vm_reset Reset a VM to a clean state. Destroys the current VM AND deletes its saved snapshot, so th Destructive snapshot_delete Delete a saved snapshot by label. This frees disk space and means the next vm_create with Execute browser_eval Run a JavaScript expression in the page context and return the result. Execute browser_navigate Navigate the sandbox Chrome to a URL via CDP (Playwright). Returns final URL and page titl Execute browser_run_test Run a Playwright test script against the browser inside a VM. Has Execute browser_wait_for Wait until a condition holds (selector visible, text appears, or network idle). Execute exec Run a shell command inside the sandbox. Returns combined stdout+stderr. Use for any CLI wo

All 36 Taw Computer 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 Taw Computer → 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? +

Kill all Chrome processes inside the sandbox. It is categorised as a Destructive tool in the Taw Computer 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 Taw Computer 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 Taw Computer. 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 Taw Computer MCP server (tawgroup/taw-computer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Taw Computer tool call.

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

CHECK YOUR STACK →