window · Mcp Selenium MCP: Risk & Policy

WHAT IT DOES

What window does on Mcp Selenium

AI agents invoke window to trigger actions in Mcp Selenium. 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 window needs a policy

Managing browser windows and tabs involves executing browser-level actions such as opening new windows, closing tabs, or switching focus. These are external operations with side effects on the browser session state. While not destructive or financial, they go beyond mere reading and constitute execution of browser automation commands.

From the tool's definition 'manages browser windows and tabs' — controlling browser windows/tabs is an external browser operation that triggers real effects (opening, closing, switching windows/tabs).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

window Rate-limited

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": {
    "window": {
      "limits": [
        {
          "counter": "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 Mcp Selenium, so you can run agents against it safely.

FAQ

Questions about window

What does the window tool do? +

manages browser windows and tabs. It is categorised as a Execute tool in the Mcp Selenium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on window? +

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

What risk level is window? +

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

Can I rate-limit window? +

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

Set action: deny in the PolicyLayer policy for 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 window? +

window is provided by the Mcp Selenium MCP server (@angiejones/mcp-selenium). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.