Tap at screen coordinates (x, y)
AI agents invoke tap to trigger actions in Enhanced ADB 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.
This tool executes a UI interaction on a real Android device. The effect is entirely context-dependent: tapping certain coordinates could open apps, confirm dialogs, submit forms, delete data, or trigger other operations. It is an action with real-world side effects, placing it firmly in Execute.
From the tool's definition Tap at screen coordinates (x, y) — performs a physical tap action on an Android device screen, triggering UI interactions whose effects depend on what is at those coordinates
Attacks that exploit this kind of access
Tap at screen coordinates (x, y). It is categorised as a Execute tool in the Enhanced ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Enhanced ADB MCP Server MCP server in PolicyLayer and add a rule for 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 Enhanced ADB MCP Server. Nothing to install.
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 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 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.
tap is provided by the Enhanced ADB MCP Server MCP server (rahulkr/r_adb_mcp_server). 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 →