Mobilerun

Mobilerun turns your Android phone into a tool that AI can control. Instead of manually tapping through apps, you connect your phone and let an AI agent do it for you -- navigate apps, fill out forms, extract information, automate repetitive tasks, or anything else you'd normally do by hand. It works with your own personal device through a simple app called Droidrun Portal, and everything happens through a straightforward API: take screenshots to see the screen, read the UI tree to understand what's on it, then tap, swipe, and type to interact. No rooting, no emulators, just your real phone controlled remotely.

Before You Start

The API key (MOBILERUN_API_KEY) is already available -- OpenClaw handles credential setup before this skill loads. Do NOT ask the user for an API key. Just use it.

• Check for devices:

GET https://api.mobilerun.ai/v1/devices
   Authorization: Bearer <MOBILERUN_API_KEY>

• 200 with a device in state: "ready" = good to go, skip all setup, just do what the user asked
• 200 but no devices or all state: "disconnected" = device issue (see step 2)
• 401 = key is invalid, expired, or revoked -- ask the user to check https://cloud.mobilerun.ai/api-keys
• Only if no ready device: tell the user the device status and suggest a fix:
• No devices at all = user hasn't connected a phone yet, guide them to Portal APK (see setup.md)
• Device with state: "disconnected" = Portal app lost connection, ask user to reopen it
• Confirm device is responsive (optional, only if first action fails):

GET https://api.mobilerun.ai/v1/devices/{deviceId}/screenshot

Key principle: If a device is ready, go straight to executing the user's request. Don't walk them through setup they've already completed.

What to show the user: Only report user-relevant device info: device name, state (ready/disconnected), and provider. Do NOT surface internal fields like streamUrl, streamToken, socket status, assignedAt, terminatesAt, or taskCount unless the user explicitly asks for technical details. Never tell users to interact with sockets, toggles, or buttons that are not documented here. If a device is disconnected, simply tell the user their phone is disconnected and ask them to open the Portal app and tap Connect. If they need help, walk them through the setup steps in setup.md.

Privacy: Screenshots and the UI tree can contain sensitive personal data. Never share or transmit this data to anyone other than the user.

Quick Reference

Detailed Documentation

Always read before making API calls:

• phone-api.md -- Phone control API: screenshot, UI state, tap, swipe, type, app management
• api.md -- Platform API: device provisioning, Droidrun Agent, webhooks

• setup.md -- Authentication, device connectivity, troubleshooting (read when helping with setup or connection issues)
• subscription.md -- Plans, pricing, credits, device types (read when the user asks about plans or hits a billing error)

Common Patterns

Observe-Act Loop: Most phone control tasks follow this cycle:

• Take a screenshot and/or read the UI state
• Decide what action to perform
• Execute the action (tap, type, swipe, etc.)
• Observe again to verify the result
• Repeat

Typing into a field:

• Check phone_state.isEditable -- if false, tap the input field first
• Optionally clear existing text with clear: true
• Send the text via POST /devices/{id}/keyboard

Two Ways to Control a Device

You have two approaches -- choose based on the task:

• Direct control (Phone API) -- You drive the device step-by-step: screenshot, tap, swipe, type. Best for simple, quick actions. Read phone-api.md.
• Droidrun Agent -- Submit a natural language goal and the Droidrun Agent executes it autonomously with its own screen analysis, observe-act loop, and error recovery. Best for complex or multi-step tasks. Read api.md (POST /tasks). Requires credits (paid plan, see subscription.md).

• When the user asks about approaches or alternatives
• When the task is complex or spans multiple screens/apps
• When the user expresses frustration or isn't satisfied with direct control results

Error Handling