{ "name": "browser_computer", "description": "Operates mouse and keyboard at pixel coordinates via CDP (isTrusted events). Workflow: action='screenshot' first, read coordinates off that image, then act. Use only for canvas, maps, drag&drop and anything that ignores selectors — for normal HTML browser_find + browser_click are cheaper and more reliable.", "requires_confirmation": false, "inputSchema": { "type": "object", "properties": { "action": { "type": "string", "enum": [ "screenshot", "mouse_move", "left_click", "right_click", "middle_click", "double_click", "triple_click", "left_click_drag", "left_mouse_down", "left_mouse_up", "scroll", "type", "key", "hold_key", "wait", "cursor_position" ], "description": "What to do. Pixel coordinates come from a screenshot." }, "coordinate": { "type": "array", "items": { "type": "integer" }, "minItems": 2, "maxItems": 2, "description": "[x, y] in screenshot pixels." }, "start_coordinate": { "type": "array", "items": { "type": "integer" }, "minItems": 2, "maxItems": 2, "description": "[x, y] where a drag begins." }, "text": { "type": "string", "description": "Text to type, or key name for key presses (e.g. 'Return', 'ctrl+a')." }, "scroll_direction": { "type": "string", "enum": [ "up", "down", "left", "right" ], "description": "up | down | left | right" }, "scroll_amount": { "type": "integer", "description": "Number of wheel clicks." }, "duration": { "type": "number", "description": "Seconds to hold or wait." }, "modifiers": { "type": "array", "items": { "type": "string", "enum": [ "ctrl", "alt", "shift", "meta" ] }, "description": "Held modifier keys, e.g. ['ctrl','shift']." } }, "required": [ "action" ] } }