browser_stop · Selenium MCP: Risk & Policy

WHAT IT DOES

What browser_stop does on SeleniumMCP

AI agents invoke browser_stop to trigger actions in SeleniumMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why browser_stop needs a policy

This tool stops a browser session, which is an action that triggers termination of an external process. While not itself destructive to data, it executes a command to manage browser state—consistent with Execute category.

From the tool's definition Tool name: 'browser_stop'; description: 'Stop the current Selenium browser session.' The tool terminates an active browser automation session, which is a subprocess control action that affects external state (the running browser process).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_stop Rate-limited

browser_stop 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches SeleniumMCP, so you can run agents against it safely.

FAQ

Questions about browser_stop

What does the browser_stop tool do? +

Stop the current Selenium browser session. It is categorised as a Execute tool in the SeleniumMCP 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_stop? +

Register the Selenium MCP server in PolicyLayer and add a rule for browser_stop: 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 SeleniumMCP. Nothing to install.

What risk level is browser_stop? +

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

Can I rate-limit browser_stop? +

Yes. Add a rate_limit block to the browser_stop 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_stop completely? +

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

browser_stop is provided by the Selenium MCP server (lokii0911/seleniummcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.