ui_find_tap
Fuzzy tap by natural language element description (Android only). When the matched element is a non-clickable label (common in grid/list items where the parent ViewGroup owns the gesture), walks up to the smallest containing clickable ancestor by default — set walkToClickable=false to tap the mat...
This record as markdown: /tools/alexgladkov-claude-in-mobile/ui-find-tap.md
What ui_find_tap does on Claude Mobile
AI agents invoke ui_find_tap to trigger actions in Claude Mobile. 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.
Why ui_find_tap is rated High
This tool triggers UI interaction (tap/click) on an Android device via ADB. It executes real gestures on a live device, which can trigger arbitrary app actions depending on what element is tapped. The effects are highly context-dependent — tapping could submit forms, delete data, make purchases, or launch operations.
From the tool's definition Fuzzy tap by natural language element description... walks up to the smallest containing clickable ancestor... tap the matched element directly
Attacks that exploit this kind of access
The rule that runs ui_find_tap safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ui_find_tap, this is the rule to start with:
ui_find_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every ui_find_tap call is checked against it from then on.
Questions about ui_find_tap
Fuzzy tap by natural language element description (Android only). When the matched element is a non-clickable label (common in grid/list items where the parent ViewGroup owns the gesture), walks up to the smallest containing clickable ancestor by default — set walkToClickable=false to tap the matched element directly. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for ui_find_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 Claude Mobile. Nothing to install.
ui_find_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 ui_find_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 ui_find_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.
ui_find_tap is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Mobile, and thousands of servers like it.
Across the catalogue