browser_close

THE RISK

High Risk

Why browser_close needs a policy

This tool executes a termination action on a running browser process. While it doesn't delete persistent data, it triggers an external operation (killing a process and closing all tabs) that could disrupt ongoing work. It's not Destructive in the data-loss sense, but it is an Execute action with side effects dependent on the current browser state.

From the tool's definition Immediately terminates the browser process and closes all open tabs

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 Web-curl MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_close:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_close": {
      "limits": [
        {
          "counter": "browser_close_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_close stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Web-curl MCP Server tools

Execute browser_flow One-call browser workflow: (optional) open URL → (optional) actions → return ONE result (s Execute fetch_api Performs a standard REST API request. Supports custom methods, headers, and request bodies Write download_file Downloads a file from a URL directly to the local file system. Ensures the destination fol Write browser_configure Set browser-wide settings (proxy, user-agent, viewport). Sessions are always persisted aut Read parse_document Downloads and extracts text content from a PDF or DOCX file at a given URL. Useful for res Read multi_search Executes multiple Google search queries in parallel. Returns a combined list of results fo

All 7 Web-curl MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Web-curl MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
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? +

Immediately terminates the browser process and closes all open tabs. Note: the browser also auto-closes after 15 minutes of inactivity. It is categorised as a Execute tool in the Web-curl MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_close? +

Register the Web-curl MCP Server 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 Web-curl MCP Server. Nothing to install.

What risk level is browser_close? +

browser_close is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

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 Web-curl MCP Server MCP server (rayss868/mcp-web-curl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Web-curl MCP Server tool call.

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

CHECK YOUR STACK →