Scroll to a specific element on the screen. Automatically finds scrollable containers and scrolls until the target element is visible.
AI agents invoke scroll_to to trigger actions in MCP Android Agent. 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 performs a UI interaction on an Android device — scrolling the screen to find and reveal an element. It triggers an external operation (physical device UI manipulation) whose effects depend on the target element argument. It fits the Execute category as it drives browser/device actions rather than simply reading data or writing persistent data.
From the tool's definition 'Scroll to a specific element on the screen. Automatically finds scrollable containers and scrolls until the target element is visible.'
Documented attack patterns abuse exactly the kind of access scroll_to gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Android Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for scroll_to:
{
"version": "1",
"default": "deny",
"tools": {
"scroll_to": {
"limits": [
{
"counter": "scroll_to_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scroll_to 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 to a specific element on the screen. Automatically finds scrollable containers and scrolls until the target element is visible. It is categorised as a Execute tool in the MCP Android Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Android Agent MCP server in PolicyLayer and add a rule for scroll_to: 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 MCP Android Agent. Nothing to install.
scroll_to 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_to 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_to. 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_to is provided by the MCP Android Agent MCP server (nim444/mcp-android-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 MCP Android Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
28 MCP Android Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.