Quickstart

Get from zero to an AI assistant operating your Android phone in four steps.

Prerequisites

An Android phone with the AGI Android app installed and signed in to your AGI platform account
Accessibility and overlay permissions granted (the app walks you through both)
An MCP client: Claude Code, Claude Desktop, Cursor, ChatGPT, or any client that supports remote MCP servers

Make your phone available

Open Settings > Developer connection in the AGI Android app. Connect or refresh the device, then confirm the page reports Connected.

Connect your MCP client

The fastest path is Claude Code:

claude mcp add --transport http agi-devices https://api.agi.tech/v1/mcp

Then run /mcp inside Claude Code and complete the browser sign-in.

Using Claude Desktop, Cursor, ChatGPT, or another client? Follow the client-specific setup on the Connect your AI client page.

Verify the connection

Ask your assistant to list your devices. It calls list_devices and should report your phone as online:

{
  "account_email": "you@example.com",
  "devices": [
    {
      "device_id": "5b6dc94d-615c-461c-b829-c5839b6986e8",
      "device_name": "samsung SM-S731U1",
      "device_model": "SM-S731U1",
      "status": "online",
      "paused": false,
      "is_default": true,
      "last_seen": "2026-08-04T00:49:41Z"
    }
  ]
}

If the tool list only contains list_devices and set_default_device, no device is registered yet - see Troubleshooting.

Run your first task

Ask in plain language:

Open Settings on my phone and tell me the battery percentage.

Under the hood, your assistant:

Calls phone_run_task with the prompt - the call returns a task_id immediately.
Waits on phone_task_monitor until the task completes.
Reads the answer from result when the task finishes with terminal: "ok".

You can watch every step happen live on the phone’s screen.

What just happened

Your MCP client                AGI cloud                 Your phone
      │                            │                          │
      │  phone_run_task(prompt)    │                          │
      ├───────────────────────────>│   queue + dispatch       │
      │        task_id             ├─────────────────────────>│
      │<───────────────────────────┤                          │
      │                            │                          │  executes with
      │  phone_task_monitor        │                          │  accessibility
      ├───────────────────────────>│    progress streamed     │  APIs
      │                            │<─────────────────────────┤
      │  status: completed,        │                          │
      │  terminal: ok, result      │                          │
      │<───────────────────────────┤                          │

Execution is asynchronous: phone_run_task never blocks on the phone, and phone_task_monitor is how your assistant waits for something actionable. If the monitor returns monitor_timed_out: true, the task is still working - call it again.

Next steps

Task lifecycle

States, terminal outcomes, and the monitor loop in depth

Task design

Write prompts that phone agents execute reliably

Tool reference

Every parameter, default, and outcome

Use cases

Messaging, daily assistant, cross-app workflows, QA

Getting Started

Devices

Sessions

Tasks

Prerequisites

What just happened

Next steps

Task lifecycle

Task design

Tool reference

Use cases

​Prerequisites

​What just happened

​Next steps

Task lifecycle

Task design

Tool reference

Use cases

Prerequisites

What just happened

Next steps