AI agents invoke scroll_up to trigger actions in Vphone. 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 a touch/input action on a virtual iOS device — it performs a physical gesture (scroll up) rather than merely reading data. It falls under Execute as it drives UI interaction on a running virtual machine. Blast radius is low since scrolling has minimal destructive potential, but it is an active control action, not passive retrieval.
From the tool's definition Scroll up on the current screen
Documented attack patterns abuse exactly the kind of access scroll_up gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vphone, and nothing reaches the server without passing your rules. This is the rule we recommend for scroll_up:
{
"version": "1",
"default": "deny",
"tools": {
"scroll_up": {
"limits": [
{
"counter": "scroll_up_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scroll_up 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 up on the current screen. It is categorised as a Execute tool in the Vphone MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vphone MCP server in PolicyLayer and add a rule for scroll_up: 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 Vphone. Nothing to install.
scroll_up 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 scroll_up 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 scroll_up. 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.
scroll_up is provided by the Vphone MCP server (pluginslab/vphone-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vphone, 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.
17 Vphone tools catalogued and risk-classified — across an index of 43,000+ MCP servers.