Mobile MCP

What is Mobile MCP about?

Enables scalable mobile automation and development through a single interface that works across iOS, Android, simulators, emulators, and real devices. Agents and LLMs can read structured accessibility trees or fall back to screenshot‑based coordinates to perform actions.

How to use Mobile MCP?

1. Install – run the server with npm using npx:

{
  "mcpServers": {
    "mobile-mcp": {
      "command": "npx",
      "args": ["-y", "@mobilenext/mobile-mcp@latest"]
    }
  }
}

Add this block to your MCP settings (e.g., Cline, Cursor, Claude Code). 2. Configure – ensure Xcode command‑line tools, Android Platform‑Tools, and Node.js v22+ are installed. Connect the desired device (simulator, emulator, or physical). 3. Invoke – from your AI‑agent client send tool calls such as mobile.getSnapshot, mobile.tap, or mobile.typeText. The server returns accessibility data or confirms actions. 4. Integrate – use with Cline, Claude Code, VS Code extensions, or any MCP‑compatible agent SDK.

Key Features

• Fast & lightweight: prefers native accessibility trees; falls back to image‑based coordinates only when needed.
• LLM‑friendly: no computer‑vision model required for most interactions.
• Deterministic: combines structured data with visual verification to reduce ambiguity.
• Structured data extraction: can return hierarchical UI information for downstream processing.
• Cross‑platform: works on iOS simulators/macOS, Android emulators on Linux/Windows/macOS, and on physical devices.

Use Cases

• Automated testing of native mobile apps without writing platform‑specific scripts.
• Data‑entry or form‑filling workflows driven by LLM instructions.
• Multi‑step user journeys (e.g., search‑comment‑share on social apps) orchestrated by an agent.
• Agent‑to‑agent communication for coordinated mobile tasks such as scraping, scheduling, or notifications.
• Extracting structured information from any on‑screen content for downstream analytics.

FAQ

Q: Do I need Xcode or Android SDK installed? A: Yes. Xcode command‑line tools are required for iOS simulators, and Android Platform‑Tools are needed for Android emulators and devices.

Q: Can the server run headlessly? A: Yes. Start an emulator or simulator in the background and launch Mobile MCP with the appropriate flags.

Q: Which agents are supported? A: Any MCP‑compatible agent, including Claude MCP, OpenAI Agent SDK, Cline, Cursor, and Copilot Studio.

Q: How does fallback to screenshot‑based actions work? A: When accessibility labels or view‑hierarchy coordinates are unavailable, the server analyses the current screenshot to calculate tap coordinates.

Q: Is there a limit on concurrent devices? A: The server can manage multiple devices simultaneously; each device is identified by its UDID or simulator name.

Mobile Next - MCP server for Mobile Development and Automation | iOS, Android, Simulator, Emulator, and physical devices

This is a Model Context Protocol (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 physical 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.

https://github.com/user-attachments/assets/c4e89c4f-cc71-4424-8184-bdbc8c638fa1

🚀 Mobile MCP Roadmap: Building the Future of Mobile

Join us on our journey as we continuously enhance Mobile MCP! Check out our detailed roadmap to see upcoming features, improvements, and milestones. Your feedback is invaluable in shaping the future of mobile automation.

👉 Explore the Roadmap

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 physical 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

• 🚀 Fast and lightweight: Uses native accessibility trees for most interactions, or screenshot based coordinates where a11y labels are not available.
• 🤖 LLM-friendly: No computer vision model required in Accessibility (Snapshot).
• 🧿 Visual Sense: Evaluates and analyses what’s actually rendered on screen to decide the next action. If accessibility data or view-hierarchy coordinates are unavailable, it falls back to screenshot-based analysis.
• 📊 Deterministic tool application: Reduces ambiguity found in purely screenshot-based approaches by relying on structured data whenever possible.
• 📺 Extract structured data: Enables you to extract structred data from anything visible on screen.

🏗️ Mobile MCP Architecture

📚 Wiki page

More details in our wiki page for setup, configuration and debugging related questions.

Installation and configuration

Setup our MCP with Cline, Cursor, Claude, VS Code, Github Copilot:

{
  "mcpServers": {
    "mobile-mcp": {
      "command": "npx",
      "args": ["-y", "@mobilenext/mobile-mcp@latest"]
    }
  }
}

Cline: To setup Cline, just add the json above to your MCP settings file. More in our wiki

Claude Code:

claude mcp add mobile -- npx -y @mobilenext/mobile-mcp@latest

Read more in our wiki! 🚀

🛠️ 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 intereactions, read information from screen, go through complex workflows. Be descriptive, straight to the point.

✨ Example Prompts

Workflows

You can specifiy 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 phone

Find 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".

More prompt examples can be found here.

Prerequisites

What you will need to connect MCP with your agent and mobile devices:

• Xcode command line tools
• Android Platform Tools
• node.js v22+
• MCP supported foundational models or agents, like Claude MCP, OpenAI Agent SDK, Copilot Studio

Simulators, Emulators, and Physical Devices

When launched, Mobile MCP can connect to:

• iOS Simulators on macOS/Linux
• Android Emulators on Linux/Windows/macOS
• Physical iOS or Android 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.

Running in "headless" mode on Simulators/Emulators

When you do not have a physical phone connected to your machine, you can run Mobile MCP with an emulator or simulator in the background.

For example, on Android:

1. Start an emulator (avdmanager / emulator command).
2. 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 list
• xcrun simctl boot "iPhone 16"

Thanks to all contributors ❤️

We appreciate everyone who has helped improve this project.