AI agents invoke drag to trigger actions in uiautomator2 MCP Server. 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.
The 'drag' tool almost certainly performs a drag gesture on an Android device UI, consistent with the server's purpose of UI automation. This is an Execute-category action as it triggers external operations (UI interaction on a device). The description is empty, which lowers confidence slightly, but the server context strongly implies this is a UI gesture action.
From the tool's definition Tool name 'drag' on a server described as controlling Android devices via uiautomator2, enabling automation like tapping, swiping, and managing apps.
Documented attack patterns abuse exactly the kind of access drag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and uiautomator2 MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for drag:
{
"version": "1",
"default": "deny",
"tools": {
"drag": {
"limits": [
{
"counter": "drag_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}drag 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.
drag. It is categorised as a Execute tool in the uiautomator2 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the uiautomator2 MCP Server MCP server in PolicyLayer and add a rule for drag: 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 uiautomator2 MCP Server. Nothing to install.
drag 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 drag 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 drag. 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.
drag is provided by the uiautomator2 MCP Server MCP server (tanbro/uiautomator2-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from uiautomator2 MCP Server, 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.
77 uiautomator2 MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.