AI agents invoke window to trigger actions in 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.
This tool controls browser window/tab management including switching focus and closing tabs. 'Close' actions have a mild destructive element, but since browser tabs can be reopened and no persistent data is necessarily lost, Execute is the most appropriate category. It triggers external browser operations whose effects depend on the action argument passed.
From the tool's definition Manage browser windows and tabs. Actions: list, switch, switch_latest, close.
Attacks that exploit this kind of access
Manage browser windows and tabs. Actions: list, switch, switch_latest, close. It is categorised as a Execute tool in the Selenium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 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 Selenium. Nothing to install.
window is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
window is provided by the Selenium MCP server (scv-consultants/selenium-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →