mcpbeat

Getting Started

facebook/getting-started

SDK setup, Swift Package Manager integration, Info.plist configuration, and first connection to Meta glasses

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
500
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/facebook/meta-wearables-dat-ios --skill getting-started

The instruction itself

9 sections, as written by the author

Getting Started with DAT SDK (iOS)

Set up the Meta Wearables Device Access Toolkit in an iOS app.

Prerequisites

  • Xcode 15.0+, iOS 16.0+ deployment target
  • Meta AI companion app installed on test device
  • Ray-Ban Meta glasses or Meta Ray-Ban Display glasses (or use MockDeviceKit for development)
  • Developer Mode enabled in Meta AI app (Settings > Your glasses > Developer Mode)

Step 1: Add the SDK via Swift Package Manager

  • In Xcode, select File > Add Package Dependencies...
  • Enter https://github.com/facebook/meta-wearables-dat-ios
  • Select a version
  • Add MWDATCore and MWDATCamera to your target

Step 2: Configure Info.plist

Add these required entries to your Info.plist:

<!-- URL scheme for Meta AI callbacks -->
<key>CFBundleURLTypes</key>
<array>
  <dict>
    <key>CFBundleTypeRole</key>
    <string>Editor</string>
    <key>CFBundleURLName</key>
    <string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
    <key>CFBundleURLSchemes</key>
    <array>
      <string>myexampleapp</string>
    </array>
  </dict>
</array>

<!-- External accessory protocol -->
<key>UISupportedExternalAccessoryProtocols</key>
<array>
  <string>com.meta.ar.wearable</string>
</array>

<!-- Background modes -->
<key>UIBackgroundModes</key>
<array>
  <string>bluetooth-peripheral</string>
  <string>external-accessory</string>
</array>
<key>NSBluetoothAlwaysUsageDescription</key>
<string>Needed to connect to Meta Wearables</string>

<!-- DAT configuration -->
<key>MWDAT</key>
<dict>
  <key>AppLinkURLScheme</key>
  <string>myexampleapp://</string>
  <key>MetaAppID</key>
  <string>0</string>
</dict>

Replace myexampleapp with your app's URL scheme. Use 0 for MetaAppID during development with Developer Mode. Also add fb-viewapp to the Info.plist URL query-schemes allowlist used by UIApplication.canOpenURL so the SDK can detect and open Meta AI.

Step 3: Initialize the SDK

Call Wearables.configure() once at app launch:

import MWDATCore

@main
struct MyApp: App {
    init() {
        do {
            try Wearables.configure()
        } catch {
            assertionFailure("Failed to configure Wearables SDK: \(error)")
        }
    }

    var body: some Scene {
        WindowGroup {
            ContentView()
        }
    }
}

Step 4: Handle URL callbacks

Your app must handle the URL callback from Meta AI after registration:

.onOpenURL { url in
    Task {
        _ = try? await Wearables.shared.handleUrl(url)
    }
}

Step 5: Register with Meta AI

func startRegistration() async throws {
    try await Wearables.shared.startRegistration()
}

Observe registration state:

Task {
    for await state in Wearables.shared.registrationStateStream() {
        // Update UI based on registration state
    }
}

Step 6: Start streaming

import MWDATCore
import MWDATCamera

// Create a DeviceSession — device selection is configured here
let wearables = Wearables.shared
let deviceSelector = AutoDeviceSelector(wearables: wearables)
let deviceSession = try wearables.createSession(deviceSelector: deviceSelector)
try deviceSession.start()

// Wait for the device session to reach the started state
for await state in deviceSession.stateStream() {
    if state == .started { break }
}

let config = StreamConfiguration(
    videoCodec: .raw,
    resolution: .low,
    frameRate: 24
)
guard let camera = try deviceSession.addCamera(config: config) else {
    return
}
let stream = camera.stream

// Observe frames
let frameToken = stream.videoFramePublisher.listen { frame in
    guard let image = frame.makeUIImage() else { return }
    Task { @MainActor in
        self.currentFrame = image
    }
}

// Start the stream capability
stream.start()

Next steps

  • Camera Streaming — Resolution, frame rate, photo capture
  • MockDevice Testing — Test without hardware
  • Session Lifecycle — Handle pause/resume/stop
  • Permissions — Camera permission flows
  • Full documentation

How to use it

Copy the folder

Take facebook/getting-started from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.