AI agents invoke browser_resize_window to trigger actions in Browser. 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.
Resizing the browser window is a browser automation action that modifies the state of a running browser instance. It doesn't read data, write persistent data, or destroy anything, but it does execute an external browser operation. Severity is low since the blast radius of misuse is minimal — it only affects window dimensions.
From the tool's definition 'Resize the browser window' — triggers a browser action that changes viewport/window dimensions
Attacks that exploit this kind of access
Resize the browser window (useful for testing responsiveness) (see browser_docs). It is categorised as a Execute tool in the Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser MCP server in PolicyLayer and add a rule for browser_resize_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 Browser. Nothing to install.
browser_resize_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 browser_resize_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 browser_resize_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.
browser_resize_window is provided by the Browser MCP server (ricardodeazambuja/browser-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 →