focus
Move the active input target to explicit X,Y screen coordinates without typing text; use semantic refs or selectors when available, then type or fill.
Instructions
Move input focus to explicit screen coordinates without entering text. Prefer semantic interactions when a snapshot ref or selector is available; use type or fill after focus. Times out after 90s.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"x": "<x>",
"y": "<y>"
},
"name": "focus"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| x | Yes | X coordinate. | |
| y | Yes | Y coordinate. | |
| udid | No | Apple device or simulator UDID. | |
| debug | No | Enable debug diagnostics. | |
| device | No | Device name; ids go in udid or serial. | |
| serial | No | Android, HarmonyOS, or Vega VVD serial. | |
| target | No | Alias for deviceTarget. | |
| session | No | Session name. | |
| noRecord | No | Do not record this action. | |
| platform | No | Device platform. | |
| includeCost | No | Add agent cost (cost.wallClockMs, …) to the result, returned as JSON text. | |
| deviceTarget | No | Device form factor. | |
| responseLevel | No | Result detail: digest (smallest) or full (largest), as JSON; default is compact text. | |
| mcpOutputFormat | No | Result text: compact optimized (default) or the full result as JSON (larger). |