AI agents invoke adb_tap to trigger actions in LocalAnt. 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 (tap gesture) on an Android device at specified coordinates. It is an external operation that triggers device-side effects depending on what is at those coordinates. Effects are not inherently destructive or financial, but misuse could trigger unintended UI actions (e.g., confirming dialogs, initiating purchases), making it Execute with medium severity.
From the tool's definition 'Tap at x,y' — triggers a touch/tap input action on a connected Android device via ADB
Attacks that exploit this kind of access
Tap at x,y. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for adb_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 LocalAnt. Nothing to install.
adb_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 adb_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 adb_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.
adb_tap is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →