Maximize the browser window.
AI agents invoke maximize_browser 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.
This tool controls a real browser window state through Selenium WebDriver. While it only resizes the window and has no data side effects, it executes an external browser operation. The blast radius is low since it only affects window display size, but it falls under Execute as it triggers an action in an external system (the browser).
From the tool's definition 'Maximize the browser window' — triggers an external browser operation via Selenium WebDriver
Attacks that exploit this kind of access
Maximize the browser window. 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.
Register the Selenium MCP Server MCP server in PolicyLayer and add a rule for maximize_browser: 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.
maximize_browser 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 maximize_browser 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 maximize_browser. 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.
maximize_browser is provided by the Selenium MCP Server MCP server (nayakprashant/selenium-mcp-server). 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 →