gets all window handles
AI agents call get_window_handles to retrieve information from Selenium MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about the current state of browser windows without modifying, executing operations, or causing destructive effects. It is a straightforward read operation that returns data about window handles. The low severity reflects minimal risk even in misuse scenarios—an agent could only learn about window state, not perform consequential actions.
From the tool's definition Tool name 'get_window_handles' and description 'gets all window handles' indicate a retrieval operation with no side effects. This is purely a query to enumerate open browser windows.
Attacks that exploit this kind of access
gets all window handles. It is categorised as a Read tool in the Selenium MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP Server MCP server in PolicyLayer and add a rule for get_window_handles: 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.
get_window_handles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_window_handles 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 get_window_handles. 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.
get_window_handles 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.
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 →