Set the browser viewport size (e.g., for mobile simulation)
AI agents invoke set_viewport to trigger actions in QA Agent Pro. 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 modifies the browser's viewport configuration, which is an external browser operation that affects subsequent page rendering and interactions. It doesn't read data, write persistent data, or destroy anything, but it does execute a browser control action that changes the runtime environment. Severity is low since the blast radius is minimal — it only affects viewport dimensions used for testing.
From the tool's definition Set the browser viewport size (e.g., for mobile simulation)
Attacks that exploit this kind of access
Set the browser viewport size (e.g., for mobile simulation). It is categorised as a Execute tool in the QA Agent Pro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the QA Agent Pro MCP server in PolicyLayer and add a rule for set_viewport: 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 QA Agent Pro. Nothing to install.
set_viewport 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 set_viewport 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 set_viewport. 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.
set_viewport is provided by the QA Agent Pro MCP server (samusilv/qa-agent-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 →