AI agents invoke tap_element_by_text 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 performs a UI interaction (tap/click) on an Android device via ADB. It executes a real action on a remote device whose effects depend on which element is tapped. This is an Execute-category action — it triggers external operations on the device (button presses, form submissions, navigation, etc.) with effects that vary by context and could be significant depending on what element is activated.
From the tool's definition 点击包含指定文本的UI元素 (Click UI element containing specified text) — triggers a tap/click action on an Android device UI element
Documented attack patterns abuse exactly the kind of access tap_element_by_text 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 tap_element_by_text:
{
"version": "1",
"default": "deny",
"tools": {
"tap_element_by_text": {
"limits": [
{
"counter": "tap_element_by_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}tap_element_by_text 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.
点击包含指定文本的UI元素. 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 tap_element_by_text: 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.
tap_element_by_text 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 tap_element_by_text 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 tap_element_by_text. 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.
tap_element_by_text 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.