mobile-mcp
This server lets AI agents and MCP clients automate and interact with iOS/Android simulators, emulators, and real devices through a unified tool interface.
Device discovery & control: list available devices, get screen size/orientation, set orientation, override GPS location, and read/write clipboard.
Cloud remote devices: log in to Mobile Next Cloud, list available remote device models, allocate/release physical cloud devices.
App management: list, resolve, inspect, launch, ensure, terminate, install, uninstall, and restore apps; launch with readiness verification and deep-link handling.
Screen interaction: take/save screenshots, list UI elements with coordinates/refs, click/double-tap/long-press, swipe, type text, and record the screen.
Input & navigation: press hardware/device buttons, open URLs/app links, and type into focused elements.
Logs & crash reports: collect device logs, list crash reports, and retrieve crash details.
Agent loop acceleration: observe compact UI scenes, estimate lookahead, get transition hints, and track task/subgoal state.
Batch automation: run multiple tools sequentially in one call, optionally listing screen elements at the end.
Allows agents to control Android emulators and real devices, including app management, UI interaction via accessibility tree and coordinates, device control, logging, and crash retrieval.
Allows agents to control iOS simulators and real devices, including app management, UI interaction via accessibility tree and coordinates, device control, logging, and crash retrieval.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mobile-mcp Describe the current UI elements on the Android emulator screen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mobile Next - MCP server for Mobile Development and Automation | iOS, Android, Simulator, Emulator, and Real Devices
This is an MCP Server that enables scalable mobile automation, development through a platform-agnostic interface, eliminating the need for distinct iOS or Android knowledge. You can run it on emulators, simulators, and real devices (iOS and Android).
This server allows Agents and LLMs to interact with native iOS/Android applications and devices through structured accessibility snapshots or coordinate-based taps based on screenshots.
Works with Claude Code, Codex, Gemini, GitHub Copilot, Antigravity — or any MCP-compatible client.
Run it against devices on your own machine, or against real iOS and Android devices in the cloud with Mobile Next Cloud — same tools, no local setup.
https://github.com/user-attachments/assets/bb084777-beb3-4930-ae6f-8d3fe694ddde
Main use cases
How we help to scale mobile automation:
📲 Native app automation (iOS and Android) for testing or data-entry scenarios.
📝 Scripted flows and form interactions without manually controlling simulators/emulators or real devices (iPhone, Samsung, Google Pixel etc)
🧭 Automating multi-step user journeys driven by an LLM
👆 General-purpose mobile application interaction for agent-based frameworks
🤖 Enables agent-to-agent communication for mobile automation usecases, data extraction
Main Features
🚀 Accessibility-first — fast and cheap: drives apps from the native accessibility tree (no vision model, no image tokens), falling back to screenshots + coordinates only when needed.
📱 One API, every target: the same tools work across iOS and Android — simulators, emulators, and real devices.
🧠 No platform expertise required: no XCUITest, no Espresso, no per-platform glue — describe the goal and the agent does it.
🧰 Full device control: taps, swipes, and gestures; app install/launch/terminate; screen recording; hardware buttons; deep links; orientation.
📊 Structured, deterministic output: reads real UI elements and extracts structured data, cutting the ambiguity of screenshot-only approaches.
🎯 Platform Support
Target | Supported | Setup |
iOS Simulator | ✅ | Xcode + a booted simulator ( |
iOS Real Device | ✅ | Device connected over USB and trusted |
Android Emulator | ✅ | Android SDK + running emulator ( |
Android Real Device | ✅ |
|
Related MCP server: Android-MCP
🔧 Available MCP Tools
Device Management
mobile_list_available_devices- List all available devices (simulators, emulators, and real devices)mobile_get_screen_size- Get the screen size of the mobile device in pixelsmobile_get_orientation- Get the current screen orientation of the devicemobile_set_orientation- Change the screen orientation (portrait/landscape)mobile_set_location- Override the GPS location reported by the device, or clear the overridemobile_clipboard- Read or replace the device clipboard
Remote Devices (Mobile Next Cloud)
mobile_login_to_cloud_provider- Authenticate this machine with the cloud device provider (browser-based device-code login)mobile_list_remote_devices- List device models available to reserve from the cloud fleetmobile_allocate_remote_device- Reserve a physical cloud device for exclusive usemobile_release_remote_device- Release a reserved cloud device back to the fleet
App Management
mobile_list_apps- List apps known by the device backend, including the current device-locale label when availablemobile_resolve_app- Resolve an app uniquely by package name or its current device-locale label; ambiguous labels are rejectedmobile_get_foreground_app- Get the app currently in the foregroundmobile_get_app_capabilities- Inspect installed/enabled/launchable metadata and whether foreground verification is supportedmobile_launch_app- Launch an app directly by package name or current device-locale label, confirming foreground by defaultmobile_wait_for_app- Wait for an app to reach the foreground and/or expose an exact visible UI targetmobile_launch_and_ready- Launch, wait for readiness, and return a fresh frame-validated screenshot snapshot in one callmobile_restore_previous_app- Return to the app that was foreground before the last verified launch/link session; screen data is re-observedmobile_ensure_app- Verify installation, optionally install a local package, and then launch with readiness verificationmobile_terminate_app- Stop and terminate a running appmobile_install_app- Install an app from file (.apk, .ipa, .app, .zip)mobile_uninstall_app- Uninstall an app using bundle ID or package name
Screen Interaction
mobile_take_screenshot- Take a screenshot to understand what's on screenmobile_save_screenshot- Save a screenshot to a filemobile_list_elements_on_screen- List UI elements with their coordinates and propertiesmobile_click_on_screen_at_coordinates- Click at coordinates, a ref, or a unique exact UI targetmobile_double_tap_on_screen- Double-tap at specific coordinatesmobile_long_press_on_screen_at_coordinates- Long press at specific coordinatesmobile_swipe_on_screen- Swipe in any direction (up, down, left, right)mobile_start_screen_recording- Start recording the device screen to a video filemobile_stop_screen_recording- Stop the active screen recording and save the video
Input & Navigation
mobile_type_keys- Type text into focused elements with optional submitmobile_press_button- Press device buttons (HOME, BACK, VOLUME_UP/DOWN, ENTER, etc.)mobile_open_url- Open URLs in the device browsermobile_open_app_link- Bind a URL/deep link to an expected app, open it, and verify that the target app reaches the foreground
Logs & Crash Reports
mobile_get_device_logs- Collect live device logs (logcat on Android, unified log on iOS), optionally saved to a filemobile_list_crashes- List crash reports available on the devicemobile_get_crash- Get the full content of a crash report by its IDmobile_batch_commands- Run multiple tools in sequence in a single call (e.g. click, type, click), optionally listing screen elements at the end
Agent loop acceleration
mobile_observe_scene- Return a compact UI Scene plus a local open/mixed/closed lookahead estimate, instead of sending a full UI dump to the model on every step.mobile_estimate_lookahead- Estimate a conservative batch size and verification cadence from local Scene evidence. This is a scheduling hint, never mutation authority.mobile_get_transition_hint- Read a short-lived, hashed hint learned from verified action-plan segments without contacting the device.mobile_agent_task_start/mobile_agent_task_update/mobile_agent_task_get- Keep bounded Planner/Orchestrator-style subgoal progress, failure codes, and replan events in the MCP runtime.
🏗️ Mobile MCP Architecture
The MCP client agent and the device runtime are intentionally separate. A client may use a Planner/Cortex/Executor loop for open-ended tasks, while the runtime uses compact Scenes, local verification, a resident native driver, and per-device safety lanes. Closed subproblems can run as bounded action-plan segments; submission, payment, permission, and interruption boundaries force a fresh observation.
The lookahead, transition-memory, and task-state components were independently implemented in TypeScript after studying the public Planner/Contextor/Cortex/Executor/Summarizer architecture in Minitap's Apache-2.0 project. See NOTICE and THIRD_PARTY_NOTICES.md for attribution and redistribution requirements.
📚 Wiki page
More details in our wiki page for setup, configuration and debugging related questions.
Prerequisites
What you will need to connect MCP with your agent and mobile devices:
node.js v20+
MCP supported foundational models or agents, like Claude MCP, OpenAI Agent SDK, Copilot Studio
Installation and configuration
Standard config works in most of the tools:
{
"mcpServers": {
"mobile-mcp": {
"command": "npx",
"args": ["-y", "@mobilenext/mobile-mcp@latest"]
}
}
}Add via the Amp VS Code extension settings screen or by updating your settings.json file:
"amp.mcpServers": {
"mobile-mcp": {
"command": "npx",
"args": [
"@mobilenext/mobile-mcp@latest"
]
}
}Amp CLI:
Run the following command in your terminal:
amp mcp add mobile-mcp -- npx @mobilenext/mobile-mcp@latestAntigravity doesn't have a CLI command to add MCP servers, so add it manually. Edit ~/.gemini/config/mcp_config.json and add:
{
"mcpServers": {
"mobile-mcp": {
"command": "npx",
"args": ["-y", "@mobilenext/mobile-mcp@latest"]
}
}
}To setup Cline, just add the json above to your MCP settings file.
Use the Claude Code CLI to add the Mobile MCP server:
claude mcp add mobile-mcp -- npx -y @mobilenext/mobile-mcp@latestFollow the MCP install guide, use json configuration above.
Use the Codex CLI to add the Mobile MCP server:
codex mcp add mobile-mcp npx "@mobilenext/mobile-mcp@latest"Alternatively, create or edit the configuration file ~/.codex/config.toml and add:
[mcp_servers.mobile-mcp]
command = "npx"
args = ["@mobilenext/mobile-mcp@latest"]For more information, see the Codex MCP documentation.
Use the Copilot CLI to interactively add the Mobile MCP server:
/mcp addYou can edit the configuration file ~/.copilot/mcp-config.json and add:
{
"mcpServers": {
"mobile-mcp": {
"type": "local",
"command": "npx",
"tools": [
"*"
],
"args": [
"@mobilenext/mobile-mcp@latest"
]
}
}
}For more information, see the Copilot CLI documentation.
Click the button to install:
Or install manually:
Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx -y @mobilenext/mobile-mcp@latest. You can also verify config or add command like arguments via clicking Edit.
Use the Gemini CLI to add the Mobile MCP server:
gemini mcp add mobile-mcp npx -y @mobilenext/mobile-mcp@latestClick the button to install:
Or install manually:
Go to Advanced settings -> Extensions -> Add custom extension. Name to your liking, use type STDIO, and set the command to npx -y @mobilenext/mobile-mcp@latest. Click "Add Extension".
Follow the MCP Servers documentation. For example in .kiro/settings/mcp.json:
{
"mcpServers": {
"mobile-mcp": {
"command": "npx",
"args": [
"@mobilenext/mobile-mcp@latest"
]
}
}
}Follow the MCP Servers documentation. For example in ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mobile-mcp": {
"type": "local",
"command": [
"npx",
"@mobilenext/mobile-mcp@latest"
],
"enabled": true
}
}
}Open Windsurf settings, navigate to MCP servers, and add a new server using the command type with:
npx @mobilenext/mobile-mcp@latestOr add the standard config under mcpServers in your settings as shown above.
✅ Verify it works
Once the server is configured, ask your agent to list devices:
list available devices
You should get back your running simulators, emulators, and connected devices. If you do, Mobile MCP is wired up correctly. If the list is empty, make sure a simulator or emulator is running (see Prerequisites) — for more help, check the wiki.
☁️ Scale up, use a cloud device
Want to scale to hundreds of devices? Use Mobile MCP in your CI/CD pipeline?
In your Agent, prompt:
log in to mobile next cloud and then show me which remote devices are available to meStreamable HTTP Server Mode
By default, Mobile MCP runs over stdio. To start a Streamable HTTP server instead, use the --listen flag:
npx @mobilenext/mobile-mcp@latest --listen 3000This binds to localhost:3000. To bind to a specific interface:
npx @mobilenext/mobile-mcp@latest --listen 0.0.0.0:3000Then configure your MCP client to connect to http://<host>:3000/mcp (or https://…/mcp behind TLS). The endpoint accepts Streamable HTTP (POST on /mcp) without an MCP session, so the transport request itself is stateless. Device lanes, screenshot snapshots, recordings, and login processes are intentionally kept in the server process; if a load balancer is used, route a device workflow to the same process (or add a shared state store before horizontal scaling). Binding to a non-loopback interface requires MOBILEMCP_AUTH.
Migration note:
--listenpreviously served the deprecated HTTP+SSE transport on/mcp. Clients must use Streamable HTTP againsthttp(s)://host:port/mcp. The old pure-SSE flow on/mcpis no longer available.
When binding to localhost, Host-header DNS rebinding protection is enabled automatically.
Authorization
To require Bearer token authorization on the HTTP server, set the MOBILEMCP_AUTH environment variable:
MOBILEMCP_AUTH=my-secret-token npx @mobilenext/mobile-mcp@latest --listen 3000When set, all requests must include the header Authorization: Bearer my-secret-token. An unauthenticated server is allowed only on loopback; --listen 0.0.0.0:3000 (or another non-loopback address) fails closed unless MOBILEMCP_AUTH is set. Browser requests with an Origin header must also be listed in MOBILEMCP_ALLOWED_ORIGINS (comma-separated) unless they use the local loopback origin.
Coordinate-safe screenshot workflow
mobile_take_screenshot returns a short-lived snapshotId together with the image dimensions, input-frame metadata, and the exact server-side transform. When tapping a point read from that image, pass the same snapshotId and coordinateSpace: "screenshot" to mobile_click_on_screen_at_coordinates. The server rejects stale snapshots, changed display geometry, points outside the image, and coordinates that round outside the half-open device viewport. This avoids relying on a rounded ratio copied from prose.
When standard mobilecli does not report coordinate units or conventions on Android, the MCP reads dumpsys display, dumpsys window displays, and adb devices -l from the authorized ADB connection and cross-checks the display size, display ID, rotation, focused window, and transport. It promotes the input frame to px / edge only when the mobilecli dimensions match the current ADB display and a live transport_id is present. If ADB is unavailable, unauthorized, inconsistent, or unparseable, the frame remains unknown and coordinate taps/swipes are refused. Set MOBILEMCP_ADB_PATH to point to a specific adb executable when it is not on PATH or in the standard Android SDK location.
For structured UI output, use format: "json" with mobile_list_elements_on_screen; it returns a pure JSON array and preserves explicit false/unknown state values.
When a stable ref is not available, the click tool also accepts an exact target object such as { "label": "Continue", "type": "Button" }. The server re-reads the UI immediately before acting and refuses zero or multiple matches; it never guesses between duplicate controls.
mobile_type_keys can take the same ref or exact target to focus an input immediately before typing. This focus step is performed inside the same per-device operation lane, so a UI refresh between listing and typing is rejected instead of sending text to an unintended field.
Direct app launch and readiness
Apps can be opened without navigating the home screen. Pass a package/bundle identifier, or pass the label returned by the device backend in its current locale (設定 on a Japanese device and Settings on an English device). Ambiguous labels are rejected rather than guessed.
Prefer mobile_launch_and_ready when the next step will interact with the app. It resolves the app, launches it, verifies the foreground app, waits for optional readiness conditions, and returns a fresh frame-validated screenshot snapshot in one call.
The default launch mode is resume, which reuses the existing app task. Use the opt-in cold mode when reproducibility requires force-stopping the package first; it may discard unsaved transient state.
{
"device": "d3befff5",
"appName": "設定",
"waitFor": {
"foreground": true,
"target": { "text": "設定" },
"timeoutMs": 15000
}
}Use MOBILEMCP_APP_ALIASES for stable team vocabulary or private apps whose localized label is not exposed by a backend. The current device-locale label is resolved dynamically and is not replaced by the static aliases.
$env:MOBILEMCP_APP_ALIASES = '{"Browser":"com.android.chrome","Internal App":"com.example.internal"}'For a shared configuration, set MOBILEMCP_APP_ALIASES_FILE to a JSON file path. Use mobile_open_app_link to bind a URL/deep link to an expected package/bundle identifier and verify that the target app becomes foreground. Custom URL schemes are rejected by default; set MOBILEMCP_ALLOW_UNSAFE_URLS=1 only when that explicit opt-in is intended.
Unknown state and cancellation behavior
If a device operation times out, is cancelled, exits abnormally, returns an invalid response, or explicitly reports an unknown result, the server never treats it as success: it quarantines that device lane. Normal follow-up operations are rejected while quarantined, preventing a later command from racing an uncertain operation. Stopping an active recording and releasing a remote device are explicit cleanup paths; they wait for in-flight work to quiesce. Only a confirmed remote release clears the old cache and quarantine state.
WebDriverAgent does not treat cancellation of the local HTTP request as proof that the device stopped. After cancellation it attempts DELETE /actions and records confirmation only when that request succeeds. Even then, the effect of the original action remains unknown, so the device stays quarantined. mobilecli 1.0.9 exposes no targeted remote-operation cancellation API, so ending the local process is reported as unconfirmed and the device is quarantined.
Clipboard values, device logs, crash bodies, stdout/stderr, response bodies, and stack traces are not copied into diagnostic logs. Tools that explicitly retrieve those values still return them to their caller; diagnostics retain only bounded error type and machine-readable failure code.
🛠️ How to Use
After adding the MCP server to your IDE/Client, you can instruct your AI assistant to use the available tools. For example, in Cursor's agent mode, you could use the prompts below to quickly validate, test and iterate on UI interactions, read information from screen, go through complex workflows. Be descriptive, straight to the point.
✨ Example Prompts
Workflows
You can specify detailed workflows in a single prompt, verify business logic, setup automations. You can go crazy:
Search for a video, comment, like and share it.
Find the video called " Beginner Recipe for Tonkotsu Ramen" by Way of
Ramen, click on like video, after liking write a comment " this was
delicious, will make it next Friday", share the video with the first
contact in your whatsapp list.Download a successful step counter app, register, setup workout and 5-star the app
Find and Download a free "Pomodoro" app that has more than 1k stars.
Launch the app, register with my email, after registration find how to
start a pomodoro timer. When the pomodoro timer started, go back to the
app store and rate the app 5 stars, and leave a comment how useful the
app is.Search in Substack, read, highlight, comment and save an article
Open Substack website, search for "Latest trends in AI automation 2025",
open the first article, highlight the section titled "Emerging AI trends",
and save article to reading list for later review, comment a random
paragraph summary.Reserve a workout class, set timer
Open ClassPass, search for yoga classes tomorrow morning within 2 miles,
book the highest-rated class at 7 AM, confirm reservation,
setup a timer for the booked slot in the phoneFind a local event, setup calendar event
Open Eventbrite, search for AI startup meetup events happening this
weekend in "Austin, TX", select the most popular one, register and RSVP
yes to the event, setup a calendar event as a reminder.Check weather forecast and send a Whatsapp/Telegram/Slack message
Open Weather app, check tomorrow's weather forecast for "Berlin", and
send the summary via Whatsapp/Telegram/Slack to contact "Lauren Trown",
thumbs up their response.Schedule a meeting in Zoom and share invite via email
Open Zoom app, schedule a meeting titled "AI Hackathon" for tomorrow at
10AM with a duration of 1 hour, copy the invitation link, and send it via
Gmail to contacts "team@example.com".Running & configuration
Environment variables
Variable | Description | Example |
| Require a Bearer token on the Streamable HTTP server ( |
|
| Comma-separated browser origins allowed to call the HTTP endpoint when an |
|
| Restrict screenshot, log, and recording artifacts to a dedicated root directory. Existing files and symbolic-link paths are never overwritten. |
|
| Path to the |
|
| JSON object mapping human-facing app aliases to a package/bundle identifier or an array of identifiers. |
|
| Path to a static JSON app-alias file. It supplements, rather than replaces, current device-locale labels. |
|
| Disable anonymous usage telemetry. |
|
| Allow |
|
| Use the legacy platform-specific robots for Android devices and physical iOS devices. iOS simulators continue to use |
|
Simulators, Emulators, and Real Devices
When launched, Mobile MCP can connect to:
iOS Simulators on macOS/Linux
Android Emulators on Linux/Windows/macOS
iOS or Android real devices (requires proper platform tools and drivers)
Make sure you have your mobile platform SDKs (Xcode, Android SDK) installed and configured properly before running Mobile Next Mobile MCP.
Telemetry
Mobile MCP collects anonymous usage telemetry via PostHog and Scarf. To disable it, set the MOBILEMCP_DISABLE_TELEMETRY environment variable:
MOBILEMCP_DISABLE_TELEMETRY=1 npx @mobilenext/mobile-mcp@latestFor json configurations:
{
"mcpServers": {
"mobile-mcp": {
"command": "npx",
"args": ["-y", "@mobilenext/mobile-mcp@latest"],
"env": {
"MOBILEMCP_DISABLE_TELEMETRY": "1"
}
}
}
}Running in "headless" mode on Simulators/Emulators
When you do not have a real device connected to your machine, you can run Mobile MCP with an emulator or simulator in the background.
For example, on Android:
Start an emulator (avdmanager / emulator command).
Run Mobile MCP with the desired flags
On iOS, you'll need Xcode and to run the Simulator before using Mobile MCP with that simulator instance.
xcrun simctl listxcrun simctl boot "iPhone 16"
🧩 Part of Mobile Next
Mobile MCP is one piece of a toolkit for driving real mobile devices:
mobilewright — "Playwright for mobile." When you're ready to turn agent-driven exploration into repeatable, deterministic tests for iOS and Android, graduate to mobilewright.
mobilecli — the universal device CLI that Mobile MCP is built on: control devices, simulators, and emulators from the command line or a JSON-RPC API.
Mobile Next Cloud — the same stack, rented: real iOS and Android devices on demand. Just prompt your agent:
log in to mobile next cloud and then show me which remote devices are available to meto get started.
🚀 Roadmap
We're continuously improving Mobile MCP. See what we're building next in ROADMAP.md — priorities are shaped heavily by community feedback, so tell us what you'd like to see.
🤝 Contributing
Contributions are welcome — code, docs, bug reports, and ideas.
⭐ Star the repo — the easiest way to help others discover Mobile MCP.
Read CONTRIBUTING.md for how to build, test, and open a pull request.
Browse open issues to find something to work on.
Questions and ideas are also welcome in our Slack community.
Please also review our Code of Conduct.
Thanks to all contributors ❤️
We appreciate everyone who has helped improve this project.
Privacy Policy
Mobile MCP runs locally and communicates only with the devices you connect. See the Mobile Next privacy policy at https://mobilenext.ai/privacy for data collection, usage, retention, and contact information.
Available Tools
39 toolsmobile_allocate_remote_deviceAllocate Remote DeviceA
Reserve a physical device from the remote cloud fleet for exclusive use, returning a device identifier usable with the other mobile_* tools. Unlike local devices, a remote device is a shared and billed resource borrowed for the session - only call this after the user has explicitly asked to use a remote/cloud device, never speculatively or as a fallback when a local device isn't found. Requires mobile_login_to_cloud_provider to have been called first; if this fails with an authentication error, call that tool then retry. Use mobile_list_remote_devices first to see which names and versions actually exist in the fleet before filtering by them. Release the device with mobile_release_remote_device once the whole task is finished - releasing wipes the device's state, so do not release and reallocate between steps of the same task just to be tidy.
Inputs: platform (required), name, type, wait, +2 more.
mobile_batch_commandsBatch CommandsADestructive
Run multiple tools in sequence in a single call, e.g. click, type, click, type. Use this to fill forms or perform multi-step flows without round-trips. The device argument is applied to every step; all steps must target that same device.
Inputs: steps (required), device (required), stopOnError, listElementsAtEnd.
mobile_click_on_screen_at_coordinatesClick ScreenA
Click on the screen at x,y coordinates, on an element by its ref (e.g. "@e5"), or on one exact unique target object with text/label/name/identifier/type. Prefer ref or a unique target when the element is listed. Ambiguous targets are rejected. Screenshot coordinates require the snapshotId returned by mobile_take_screenshot; the server validates that the display and geometry have not changed before tapping.
Inputs: device (required), x, y, ref, +3 more.
mobile_clipboardClipboardA
Read or replace the device clipboard. Pass text to set the clipboard, omit it to read the current clipboard.
Inputs: device (required), text.
mobile_double_tap_on_screenDouble Tap ScreenB
Double-tap on the screen at given x,y coordinates.
Inputs: x (required), y (required), device (required).
mobile_ensure_appEnsure AppA
Ensure an app is installed, optionally install it from a local package when it is missing, and optionally launch it with foreground/readiness verification. Use mobile_launch_and_ready when a screenshot snapshot is needed in the same call.
Inputs: device (required), mode, launch, locale, +4 more.
mobile_get_app_capabilitiesGet App CapabilitiesARead-only
Inspect the app inventory record used for resolution and launch planning. Reports whether the backend knows the app as installed, enabled, and launchable; unknown fields remain explicit instead of being inferred.
Inputs: device (required), appName, packageName.
mobile_get_crashGet Crash ReportARead-only
Get the full content of a crash report by its ID. Use mobile_list_crashes to find available crash IDs.
Inputs: id (required), device (required).
mobile_get_device_logsGet Device LogsA
Collect live device logs (logcat on Android, unified log on iOS) as one JSON object per line. Only logs emitted after the call starts are captured, so trigger the behavior you want to observe right before or during the call. Stops after limit entries or after 30 seconds of silence. Each line of a stack trace counts as one entry, so filter by process or tag to avoid filling the limit with noise. Start with a small limit (20-50) for a quick look. For large captures, pass saveTo to write logs to a file and only the entry count is returned.
Inputs: device (required), limit, filter, saveTo.
mobile_get_foreground_appGet Foreground AppARead-only
Get the app currently in the foreground on the device. Use this to verify which app or screen you are on before interacting with it.
Inputs: device (required).
mobile_get_orientationGet OrientationBRead-only
Get the current screen orientation of the device
Inputs: device (required).
mobile_get_screen_sizeGet Screen SizeARead-only
Get the screen size of the mobile device in pixels
Inputs: device (required).
mobile_install_appInstall AppC
Install an app on mobile device
Inputs: path (required), device (required).
mobile_launch_and_readyLaunch And ReadyA
Launch an app directly, wait until it is confirmed ready, and return a fresh frame-validated screenshot snapshot for immediate interaction. This is the preferred one-call app entry point for agents.
Inputs: device (required), mode, scale, locale, +4 more.
mobile_launch_appLaunch AppA
Launch an app directly without navigating the home screen. Identify it by packageName or by the label in the device's current locale. By default, wait until the requested app is confirmed in the foreground; use mobile_launch_and_ready when a fresh validated screenshot is also needed.
Inputs: device (required), mode, locale, appName, +2 more.
mobile_list_appsList AppsARead-only
List apps known by the device backend, including the current device-locale label when available. Use mobile_resolve_app to resolve a human-facing name without guessing.
Inputs: device (required).
mobile_list_available_devicesList DevicesARead-only
List all available devices. This includes both physical mobile devices and mobile simulators and emulators. It returns both Android and iOS devices. These are local devices already connected to this machine, ready to use immediately at no cost - for devices from the shared remote cloud fleet, use mobile_list_remote_devices instead.
Inputs: no named parameters.
mobile_list_crashesList Crash ReportsARead-only
List crash reports available on the device
Inputs: device (required).
mobile_list_elements_on_screenList Screen ElementsARead-only
List elements on screen with their ref, coordinates, and display text or accessibility label. Use the ref with mobile_click_on_screen_at_coordinates. Refs and coordinates stay valid as long as the screen does not change; re-list only after navigation or a layout change.
Inputs: device (required), format.
mobile_list_remote_devicesList Remote DevicesARead-only
List the catalog of device models (make, platform, OS version) available to reserve from the remote cloud device fleet. This is different from mobile_list_available_devices, which lists real devices and simulators/emulators already connected to this local machine and ready to use immediately at no cost. Remote devices live in a shared cloud fleet: they are not usable until reserved with mobile_allocate_remote_device, and reserving one may be a limited/billed resource. Requires mobile_login_to_cloud_provider to have been called first; if this fails with an authentication error, call that tool then retry.
Inputs: no named parameters.
mobile_login_to_cloud_providerLogin to Cloud ProviderA
Start authenticating this machine with the remote device cloud provider. This is required once before mobile_list_remote_devices or mobile_allocate_remote_device will work; if either of those fails with an authentication error, call this tool and then retry. This starts a browser-based device-code login and returns quickly with a URL and a one-time code - it does NOT wait for the login to complete. Show the URL and code to the user verbatim and ask them to open the URL and enter the code in their own browser. The login keeps running in the background after this tool returns; once the user confirms they've completed it, retry the remote devices tool that originally failed. Only call this after the user has explicitly asked to connect to, log into, or use remote/cloud devices - never call it speculatively, since it interrupts the user to act in their browser.
Inputs: no named parameters.
mobile_long_press_on_screen_at_coordinatesLong Press ScreenA
Long press on the screen at given x,y coordinates. If long pressing on an element, use the mobile_list_elements_on_screen tool to find the coordinates.
Inputs: x (required), y (required), device (required), duration.
mobile_open_app_linkOpen App LinkA
Open a URL or app deep link and verify that the requested app becomes foreground. Use packageName or the device-locale appName to bind the expected destination; unknown or dangerous URL schemes remain blocked unless explicitly allowed by MOBILEMCP_ALLOW_UNSAFE_URLS=1.
Inputs: url (required), device (required), appName, waitFor, +1 more.
mobile_open_urlOpen URLA
Open a URL in browser on device
Inputs: url (required), device (required).
mobile_press_buttonPress ButtonC
Press a button on device
Inputs: button (required), device (required).
mobile_release_remote_deviceRelease Remote DeviceADestructive
Release a device previously reserved with mobile_allocate_remote_device back to the remote cloud fleet so it becomes available to others. Releasing is destructive to the device's state: apps installed, files pushed, and any other changes made during this session are lost, and a later mobile_allocate_remote_device call may take time and could return a different physical unit. Only release once the whole task is finished - if there is more work to do on the same device shortly, keep holding it rather than releasing and reallocating.
Inputs: device (required).
mobile_resolve_appResolve AppARead-only
Resolve an app by package name or by the app label currently exposed by the device locale. Matching is exact after Unicode/whitespace normalization; ambiguous labels are rejected instead of guessed.
Inputs: device (required), appName, packageName.
mobile_restore_previous_appRestore Previous AppA
Return to the app that was foreground before the last verified app launch or app-link session. The destination is re-observed and old screenshots/refs are not restored.
Inputs: device (required).
mobile_save_screenshotSave ScreenshotB
Save a screenshot of the mobile device to a file
Inputs: device (required), saveTo (required), scale, maxSize.
mobile_set_locationSet LocationA
Override the GPS location reported by the device, or clear the override to restore the real location. Omit latitude and longitude to clear.
Inputs: device (required), latitude, longitude.
mobile_set_orientationSet OrientationA
Change the screen orientation of the device
Inputs: device (required), orientation (required).
mobile_start_screen_recordingStart Screen RecordingA
Start recording the screen of a mobile device. The recording runs in the background until stopped with mobile_stop_screen_recording. Returns the path where the recording will be saved.
Inputs: device (required), output, timeLimit.
mobile_stop_screen_recordingStop Screen RecordingA
Stop an active screen recording on a mobile device. Returns the file path, size, and approximate duration of the recording.
Inputs: device (required).
mobile_swipe_on_screenSwipe ScreenC
Swipe on the screen
Inputs: device (required), direction (required), x, y, +2 more.
mobile_take_screenshotTake ScreenshotARead-only
Take a screenshot of the mobile device and create a short-lived, frame-validated snapshot. Use the returned snapshotId with mobile_click_on_screen_at_coordinates and coordinateSpace=screenshot when tapping a point read from this image. Do not cache this result beyond the snapshot lifetime.
Inputs: device (required), scale, maxSize.
mobile_terminate_appTerminate AppA
Stop and terminate an app on mobile device. Identify it by package name or by its current device-locale label.
Inputs: device (required), appName, packageName.
mobile_type_keysType TextA
Type text into the focused element. Optionally provide a ref or exact target to focus immediately before typing; ambiguous or stale targets are rejected.
Inputs: text (required), device (required), submit (required), ref, +1 more.
mobile_uninstall_appUninstall AppADestructive
Uninstall an app from mobile device
Inputs: device (required), bundle_id (required).
mobile_wait_for_appWait For AppARead-only
Wait until an app is in the foreground and/or an exact visible UI target appears. This is read-only and does not launch, terminate, or otherwise change the app.
Inputs: device (required), appName, waitFor, packageName.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 39 tools
Most tools have clearly distinct purposes, but a few near-overlaps exist among app-launching tools (mobile_launch_app, mobile_launch_and_ready, mobile_ensure_app) and between mobile_take_screenshot and mobile_save_screenshot. Descriptions are detailed enough to disambiguate with care, so agents should rarely misselect.
All tools follow the consistent mobile_verb_noun pattern, with clear verbs like list, get, set, launch, click, swipe, and take. Even compound actions like mobile_launch_and_ready and prepositions like on_screen are used consistently across the set, making the naming predictable and readable.
At 39 tools, this is well above the 25-tool threshold for 'too many' even for a broad mobile automation domain. While each tool has a specific purpose, the sheer number risks overwhelming an agent and suggests some tools could be consolidated (e.g., combining screenshot save/take or merging device listing variants).
The tool set covers the full mobile lifecycle: device discovery/reservation, app management (install, launch, terminate, ensure), UI interaction (clicks, gestures, typing), screenshots, orientation, location, clipboard, logs, crash reports, screen recording, and a batch execution tool. There are no obvious dead ends or missing critical operations for the stated purpose.
Related MCP Connectors
Let your AI agent control real iPhones: screenshots, tap, swipe, type and open apps.
Let AI agents control Android and iOS devices on Mobilerun Cloud: screen, input, apps, workflows.
Drive real devices from your AI Coding tool. Embed a client SDK (Unity, Godot, Flutter, iOS/macOS, Android, React Native, Web) in your app, then capture screenshots, traverse the UI tree, inject taps and key events, and run automated test tasks on the physical device over a secure relay.
Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI agents to interact with Android devices through UI manipulation, screen capture, touch gestures, text input, and app management via ADB. Provides comprehensive mobile automation capabilities including element detection, navigation, and application control for Android device testing and interaction.9123 PyPI2-
- AlicenseBqualityDmaintenanceEnables AI agents to control Android devices and emulators through direct UI interaction, allowing app navigation, automated testing, and real-world task execution via ADB without computer vision or scripts.182MIT

MobAI MCP Serverofficial
AlicenseAqualityCmaintenanceEnables AI assistants to automate mobile devices (Android and iOS) through a single DSL interface, supporting actions like tap, type, swipe, and assertions.20426 npm255Apache 2.0- AlicenseBqualityDmaintenanceEnables AI agents to inspect, log, and control React Native apps on Android emulators or iOS simulators, including UI tree, tap, scroll, and hot reload.2246 npm5MIT