switch_to_window · Selenium MCP Server MCP: Risk & Policy

WHAT IT DOES

What switch_to_window does on Selenium MCP Server

AI agents invoke switch_to_window to trigger actions in Selenium MCP Server. 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 switch_to_window needs a policy

Switching browser windows is a browser automation action that changes the active execution context. While it doesn't directly read or write data, it directs subsequent browser operations to a different window, making it an Execute-category action. Misuse could redirect agent actions to unintended browser contexts, but blast radius is moderate since it doesn't directly cause data loss or financial harm.

From the tool's definition "switches to a specific window by handle" — controls browser window focus/context via Selenium WebDriver

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

switch_to_window Rate-limited

switch_to_window 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": {
    "switch_to_window": {
      "limits": [
        {
          "counter": "switch_to_window_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 Selenium MCP Server, so you can run agents against it safely.

FAQ

Questions about switch_to_window

What does the switch_to_window tool do? +

switches to a specific window by handle. It is categorised as a Execute tool in the Selenium 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 switch_to_window? +

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

What risk level is switch_to_window? +

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

Can I rate-limit switch_to_window? +

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

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

switch_to_window is provided by the Selenium MCP Server MCP server (jyothishkumarav/selenium-mcp-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.