AI agents invoke multi_tap to trigger actions in Adb. 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 executes UI input actions (multi-touch taps) on an Android device via ADB. It doesn't read data or write persistent data, but performs external operations (screen touch events) whose effects depend on where taps are directed. Misuse could trigger unintended UI interactions, button presses, or app actions on the device.
From the tool's definition 多点点击屏幕 (multi-tap the screen) — triggers physical touch input actions on a remote Android device
Documented attack patterns abuse exactly the kind of access multi_tap gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adb, and nothing reaches the server without passing your rules. This is the rule we recommend for multi_tap:
{
"version": "1",
"default": "deny",
"tools": {
"multi_tap": {
"limits": [
{
"counter": "multi_tap_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}multi_tap 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.
多点点击屏幕. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb MCP server in PolicyLayer and add a rule for multi_tap: 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 Adb. Nothing to install.
multi_tap 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 multi_tap 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 multi_tap. 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.
multi_tap is provided by the Adb MCP server (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, 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.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.