AI agents invoke browser_scroll 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.
Scrolling is a browser action that executes a UI interaction within the automated browser. While it has minimal direct harm potential, it is an Execute-category action because it triggers an external operation (browser scroll event) whose effect depends on arguments (scroll position/direction). It cannot be classified as Read since it causes a side effect in the browser state.
From the tool's definition 'Scroll the page' — triggers a browser interaction/action in a real browser automation context
Documented attack patterns abuse exactly the kind of access browser_scroll 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_scroll:
{
"version": "1",
"default": "deny",
"tools": {
"browser_scroll": {
"limits": [
{
"counter": "browser_scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_scroll 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.
Scroll the page. 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_scroll: 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_scroll 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_scroll 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_scroll. 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_scroll 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.