# Mobile device automation with artificial intelligence

Mobile-mcp is a Model Context Protocol server that performs automation and web scraping operations on mobile devices and simulators. This tool enables artificial intelligence models to interact directly with iOS and Android platforms to execute tasks.

- ★ 9,957
- TypeScript
- GitHub Trending · 2026-09-27

## Updates

- **October 25, 2026:** Stars 9,754 → 9,957, latest release 1.0.13 (October 24, 2026).
- **October 19, 2026:** Stars 9,483 → 9,754, latest release 1.0.12 (October 18, 2026).
- **October 15, 2026:** Stars 9,015 → 9,483, latest release 1.0.11 (October 14, 2026).
- **October 12, 2026:** Stars 8,808 → 9,015, latest release 1.0.10 (October 11, 2026).

## What you get

- Performing application testing on iOS and Android devices
- automatically scanning screen elements and extracting structured data
- managing emulators and simulators through a single interface

## Installation

**Setup with Claude**

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

**Running Directly**

```
npx @mobilenext/mobile-mcp@latest
```

## Running it

**Start the Server**

```
npx @mobilenext/mobile-mcp@latest
```

## If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

List the applications on the connected mobile devices and scan the elements on the screen using the Model Context Protocol server that communicates with the mobile development tools on my computer.

Repository: https://github.com/mobile-next/mobile-mcp. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

## Related dictionary terms

- [Web Scraping](https://trescout.com/en/dictionary/web-scraping/)
- [Context](https://trescout.com/en/dictionary/context/)
- [MCP](https://trescout.com/en/dictionary/mcp/)
- [Artificial Intelligence](https://trescout.com/en/dictionary/artificial-intelligence/)

- **Who it is for:** It is intended for developers who want to manage mobile application testing and automation processes with artificial intelligence agents.
- **License:** Apache-2.0

## Links

- [GitHub repository →](https://github.com/mobile-next/mobile-mcp)
- [Read in Turkish →](https://trescout.com/discover/mobile-mcp/)

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-27: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was **machine-translated** from the Turkish original · the Turkish version prevails.

---
Source: TreScout Discover · https://trescout.com/en/discover/mobile-mcp/