AI agents invoke browser_viewport_set to trigger actions in Termux Browser Pilot. 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 triggers an external browser operation (resizing the window), which is an action with side effects on a running browser instance. It does not read data, write/create content, delete anything, or involve finances. It fits Execute as it manipulates a live browser environment. Severity is low since misuse has minimal blast radius.
From the tool's definition Resize the browser window
Documented attack patterns abuse exactly the kind of access browser_viewport_set gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Termux Browser Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_viewport_set:
{
"version": "1",
"default": "deny",
"tools": {
"browser_viewport_set": {
"limits": [
{
"counter": "browser_viewport_set_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} browser_viewport_set stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Resize the browser window. It is categorised as a Execute tool in the Termux Browser Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Termux Browser Pilot MCP server in PolicyLayer and add a rule for browser_viewport_set: 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 Termux Browser Pilot. Nothing to install.
browser_viewport_set 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_viewport_set 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_viewport_set. 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_viewport_set is provided by the Termux Browser Pilot MCP server (salviz/termux-browser-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Termux Browser Pilot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
148 Termux Browser Pilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.