What are the prerequisites?
Node.js 18+ and the MobAI desktop app running locally on port 8686 with a connected Android or iOS device (or emulator/simulator).
Mobai MCP Server
@MobAI-App
Basic information
About Mobai MCP Server
MCP (Model Context Protocol) server for MobAI (https://mobai.run) - AI-powered mobile device automation. This server enables AI coding assistants like Cursor, Windsurf, Cline, and other MCP-compatible tools to control Android and iOS devices, emulators, and simulators.
Mobai MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mobai": {
"command": "npx",
"args": [
"-y",
"mobai-mcp"
]
}
}
}Mobai MCP Server tools
22List all connected Android and iOS devices, emulators, and simulators
Get information about a specific device
Start the on-device bridge (accessibility service on Android, WebDriverAgent on iOS). Required before automation.
Stop the on-device bridge
Capture a screenshot from the device. Returns the file path to the saved PNG.
Get the UI accessibility tree showing all visible elements with indices for tapping
Tap an element by index (from UI tree) or coordinates
Type text on the device (tap input field first to focus)
Perform a swipe gesture
Navigate to device home screen
Launch an application by bundle ID
List installed applications on the device
Perform OCR text recognition on the current screen (iOS only). Returns detected text with screen coordinates for tapping (already adjusted for tapping).
Execute a batch of automation steps using the DSL (Domain Specific Language). This is the PREFERRED method for complex automation as it's more reliable than sequential API calls. DSL supports: observe, tap, type, toggle, swipe, scroll, open_app, navigate, wait_for, assert_*, if_exists, delay, execute_js (web) Example DSL script: { "version": "0.2", "steps": [ {"action": "observe", "context": "native", "include": ["ui_tree"]}, {"action": "tap", "predicate": {"text_contains": "Settings"}}, {"action": "delay", "duration_ms": 500}, {"action": "observe", "context": "native", "include": ["ui_tree"]} ], "on_fail": {"strategy": "retry", "max_retries": 2} }
Run an AI agent to perform a task autonomously. The agent will observe the screen, make decisions, and execute actions to complete the task.
List available web pages (browser tabs and WebViews) for web automation
Navigate to a URL in the browser
Get the DOM tree of the current web page
Click an element in the web page using CSS selector
Type text into a web element using CSS selector
Execute JavaScript in the web page context
Make a raw HTTP request to the MobAI API. Use this for advanced operations not covered by other tools. Base URL: http://127.0.0.1:8686/api/v1 Common endpoints: - GET /devices - List devices - GET /devices/{id}/screenshot - Take screenshot - GET /devices/{id}/ui-tree - Get UI tree - POST /devices/{id}/dsl/execute - Execute DSL script - POST /devices/{id}/agent/run - Run AI agent
Overview
What is MobAI MCP?
MobAI MCP is a Model Context Protocol server for MobAI, an AI-powered mobile device automation platform. It enables AI coding assistants like Cursor, Windsurf, Cline, and other MCP-compatible tools to control Android and iOS devices, emulators, and simulators.
How to use MobAI MCP?
Run the server via npx -y mobai-mcp and configure it as an MCP server in your AI tool's settings. For example, in Cursor add to .cursor/mcp.json with the command and args shown above. The server uses stdio transport.
Key features of MobAI MCP
- Device Control: List, connect, and manage Android/iOS devices
- UI Automation: Tap, type, swipe, and interact with native apps
- Web Automation: Control Safari/Chrome and WebViews with CSS selectors
- DSL Batch Execution: Execute multiple automation steps efficiently
- AI Agent: Run autonomous agents to complete complex tasks
- Screenshot Capture: Capture and save device screenshots
Use cases of MobAI MCP
- List connected devices and capture screenshots for visual inspection
- Automate native apps (e.g., open Settings and navigate to General)
- Run autonomous AI agents to complete multi-step tasks like enabling Wi-Fi
- Perform web automation in Safari/Chrome and WebViews
Frequently asked questions
How does this compare to the Claude Code Plugin?
The MCP server provides the same functionality as the Claude Code Plugin but works with any MCP-compatible AI client, offering named tools and resources instead of generic HTTP requests and markdown skills.
What should I do if I get a "Connection refused" error?
Ensure the MobAI desktop app is running and the API is available at `http://127.0.0.1:8686`.
What should I do if I get a "Bridge not running" error?
Use the `start_bridge` tool first before automation. On iOS, the bridge may take up to 60 seconds to start.
Where are screenshots saved?
Screenshots are saved to `/tmp/mobai/screenshots/`. Use your AI tool’s file reading capability to view them.
More Other MCP servers
Handl
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Codelf
unbugA search tool helps dev to solve the naming things problem.
14.2K
The Living Bread
The Living BreadA free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
Screenpipe
screenpipeYC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
22.0K
Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
88.2K
Comments