Run adb shell input tap with x/y coordinates.
AI agents invoke android_tap to trigger actions in DevLab MCP Suite. 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 an adb shell command that triggers a UI interaction (tap) on an Android device. The effect depends on the coordinates provided and whatever UI element resides there — it could trigger any action including confirmations, deletions, or purchases.
From the tool's definition 'Run adb shell input tap with x/y coordinates' — directly executes an adb shell command to simulate a tap on the device screen
Attacks that exploit this kind of access
Run adb shell input tap with x/y coordinates. It is categorised as a Execute tool in the DevLab MCP Suite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DevLab MCP Suite MCP server in PolicyLayer and add a rule for android_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 DevLab MCP Suite. Nothing to install.
android_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 android_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 android_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.
android_tap is provided by the DevLab MCP Suite MCP server (tanguito86/devlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →