@mobilenext/mobile-mcp 0.0.23 → 0.0.24

package/lib/android.js

@@ -73,11 +73,6 @@ class AndroidRobot {
             timeout: TIMEOUT,
         });
     }
-    getFirstDisplayId() {
-        const output = this.adb("shell", "dumpsys", "SurfaceFlinger", "--display-id").toString();
-        const match = output.match(/Display (\d+) \(/);
-        return match ? match[1] : null;
-    }
     getSystemFeatures() {
         return this.adb("shell", "pm", "list", "features")
             .toString()
@@ -195,16 +190,42 @@ class AndroidRobot {
         }
         this.adb("shell", "input", "swipe", `${x0}`, `${y0}`, `${x1}`, `${y1}`, "1000");
     }
-    async getScreenshot() {
-        const displayId = this.getFirstDisplayId();
-        if (displayId !== null) {
-            // always good to provide displayId. required for multi-display devices such as fold
-            return this.adb("exec-out", "screencap", "-p", "-d", displayId);
+    getDisplayCount() {
+        return this.adb("shell", "dumpsys", "SurfaceFlinger", "--display-id")
+            .toString()
+            .split("\n")
+            .filter(s => s.startsWith("Display "))
+            .length;
+    }
+    getFirstDisplayId() {
+        const displays = this.adb("shell", "cmd", "display", "get-displays")
+            .toString()
+            .split("\n")
+            .filter(s => s.startsWith("Display id "))
+            // filter for state ON even though get-displays only returns turned on displays
+            .filter(s => s.indexOf(", state ON,") >= 0)
+            // another paranoia check
+            .filter(s => s.indexOf(", uniqueId ") >= 0);
+        if (displays.length > 0) {
+            const m = displays[0].match(/uniqueId \"([^\"]+)\"/);
+            if (m !== null) {
+                const displayId = m[1];
+                if (displayId.indexOf("local:") === 0) {
+                    return displayId.split(":")[1];
+                }
+                return displayId;
+            }
         }
-        else {
-            // backward compatibility for android 10 and below
+        return null;
+    }
+    async getScreenshot() {
+        if (this.getDisplayCount() <= 1) {
+            // backward compatibility for android 10 and below, and for single display devices
             return this.adb("exec-out", "screencap", "-p");
         }
+        // find the first display that is turned on, and capture that one
+        const displayId = this.getFirstDisplayId();
+        return this.adb("exec-out", "screencap", "-p", "-d", `${displayId}`);
     }
     collectElements(node) {
         const elements = [];
@@ -287,16 +308,21 @@ class AndroidRobot {
         if (!BUTTON_MAP[button]) {
             throw new robot_1.ActionableError(`Button "${button}" is not supported`);
         }
-        this.adb("shell", "input", "keyevent", BUTTON_MAP[button]);
+        const mapped = BUTTON_MAP[button];
+        this.adb("shell", "input", "keyevent", mapped);
     }
     async tap(x, y) {
         this.adb("shell", "input", "tap", `${x}`, `${y}`);
     }
+    async longPress(x, y) {
+        // a long press is a swipe with no movement and a long duration
+        this.adb("shell", "input", "swipe", `${x}`, `${y}`, `${x}`, `${y}`, "500");
+    }
     async setOrientation(orientation) {
-        const orientationValue = orientation === "portrait" ? 0 : 1;
+        const value = orientation === "portrait" ? 0 : 1;
         // disable auto-rotation prior to setting the orientation
         this.adb("shell", "settings", "put", "system", "accelerometer_rotation", "0");
-        this.adb("shell", "content", "insert", "--uri", "content://settings/system", "--bind", "name:s:user_rotation", "--bind", `value:i:${orientationValue}`);
+        this.adb("shell", "content", "insert", "--uri", "content://settings/system", "--bind", "name:s:user_rotation", "--bind", `value:i:${value}`);
     }
     async getOrientation() {
         const rotation = this.adb("shell", "settings", "get", "system", "user_rotation").toString().trim();

package/lib/ios.js

@@ -117,6 +117,10 @@ class IosRobot {
         const wda = await this.wda();
         await wda.tap(x, y);
     }
+    async longPress(x, y) {
+        const wda = await this.wda();
+        await wda.longPress(x, y);
+    }
     async getElementsOnScreen() {
         const wda = await this.wda();
         return await wda.getElementsOnScreen();

package/lib/iphone-simulator.js

@@ -104,6 +104,10 @@ class Simctl {
         const wda = await this.wda();
         return wda.tap(x, y);
     }
+    async longPress(x, y) {
+        const wda = await this.wda();
+        return wda.longPress(x, y);
+    }
     async pressButton(button) {
         const wda = await this.wda();
         return wda.pressButton(button);

package/lib/server.js

@@ -229,6 +229,14 @@ const createMcpServer = () => {
         await robot.tap(x, y);
         return `Clicked on screen at coordinates: ${x}, ${y}`;
     });
+    tool("mobile_long_press_on_screen_at_coordinates", "Long press on the screen at given x,y coordinates. If long pressing on an element, use the list_elements_on_screen tool to find the coordinates.", {
+        x: zod_1.z.number().describe("The x coordinate to long press on the screen, in pixels"),
+        y: zod_1.z.number().describe("The y coordinate to long press on the screen, in pixels"),
+    }, async ({ x, y }) => {
+        requireRobot();
+        await robot.longPress(x, y);
+        return `Long pressed on screen at coordinates: ${x}, ${y}`;
+    });
     tool("mobile_list_elements_on_screen", "List elements on screen and their coordinates, with display text or accessibility label. Do not cache this result.", {
         noParams
     }, async ({}) => {

package/lib/webdriver-agent.js

@@ -142,6 +142,32 @@ class WebDriverAgent {
             });
         });
     }
+    async longPress(x, y) {
+        await this.withinSession(async (sessionUrl) => {
+            const url = `${sessionUrl}/actions`;
+            await fetch(url, {
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/json",
+                },
+                body: JSON.stringify({
+                    actions: [
+                        {
+                            type: "pointer",
+                            id: "finger1",
+                            parameters: { pointerType: "touch" },
+                            actions: [
+                                { type: "pointerMove", duration: 0, x, y },
+                                { type: "pointerDown", button: 0 },
+                                { type: "pause", duration: 500 },
+                                { type: "pointerUp", button: 0 }
+                            ]
+                        }
+                    ]
+                }),
+            });
+        });
+    }
     isVisible(rect) {
         return rect.x >= 0 && rect.y >= 0;
     }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mobilenext/mobile-mcp",
-  "version": "0.0.23",
+  "version": "0.0.24",
   "description": "Mobile MCP",
   "repository": {
     "type": "git",