iOS Device Automation

iOS Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW: 1. Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop. 2. Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together. 3. Allow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer. 4. Always report task results before finishing. After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.

Automate iOS devices using npx -y @midscene/ios@1. Each CLI command maps directly to an MCP tool — you (the AI agent) act as the brain, deciding which actions to take based on screenshots.

What act Can Do

Inside a single act call on iOS, Midscene can tap, double-tap, long-press, type, clear text, scroll, drag items, zoom with two fingers, press keys, and use system navigation such as Home or the app switcher while working from the current visible screen.

Prerequisites

Midscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):

MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"

Example: Gemini (Gemini-3-Flash)

MIDSCENE_MODEL_API_KEY="your-google-api-key"
MIDSCENE_MODEL_NAME="gemini-3-flash"
MIDSCENE_MODEL_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai/"
MIDSCENE_MODEL_FAMILY="gemini"

Example: Qwen 3.5

MIDSCENE_MODEL_API_KEY="your-aliyun-api-key"
MIDSCENE_MODEL_NAME="qwen3.5-plus"
MIDSCENE_MODEL_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
MIDSCENE_MODEL_FAMILY="qwen3.5"
MIDSCENE_MODEL_REASONING_ENABLED="false"
# If using OpenRouter, set:
# MIDSCENE_MODEL_API_KEY="your-openrouter-api-key"
# MIDSCENE_MODEL_NAME="qwen/qwen3.5-plus"
# MIDSCENE_MODEL_BASE_URL="https://openrouter.ai/api/v1"

Example: Doubao Seed 2.0 Lite

MIDSCENE_MODEL_API_KEY="your-doubao-api-key"
MIDSCENE_MODEL_NAME="doubao-seed-2-0-lite"
MIDSCENE_MODEL_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
MIDSCENE_MODEL_FAMILY="doubao-seed"

Commonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.

If the model is not configured, ask the user to set it up. See Model Configuration for supported providers.

Commands

Connect to Device

npx -y @midscene/ios@1 connect

If WebDriverAgent is already running and the session was created outside Midscene, pass the WDA endpoint and external session ID together:

npx -y @midscene/ios@1 connect --wda-host 127.0.0.1 --wda-port 8100 --session-id <sessionId>

Use the same --wda-host, --wda-port, and --session-id options on later commands when you want them to operate through that existing WDA session.

Launch an App, URL, or Deep Link

Use the built-in launch capability when you want to start from a known app or route before the rest of the task. Give it the most specific target you have, such as a bundle ID, web URL, deep link, or phone/mail link. Typical targets include com.apple.Preferences, https://www.apple.com, myapp://profile/user/123, and tel:+1234567890.

Send a Direct Device Request

Use this when the task needs lower-level device control instead of a normal visible UI interaction:

npx -y @midscene/ios@1 runwdarequest --method GET --endpoint /wda/screen

This does not run an ADB command. On iOS, the underlying operation is an HTTP request to WebDriverAgent, typically GET http://<wdaHost>:<wdaPort>/session/<sessionId>/wda/screen.

Take Screenshot

npx -y @midscene/ios@1 take_screenshot

After taking a screenshot, read the saved image file to understand the current screen state before deciding the next action.

Perform Action

Use act to interact with the device and get the result. It autonomously handles all UI interactions internally — tapping, typing, scrolling, swiping, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe what you want to do and the desired effect in natural language:

# specific instructions
npx -y @midscene/ios@1 act --prompt "type hello world in the search field and press Enter"
npx -y @midscene/ios@1 act --prompt "tap Delete, then confirm in the alert dialog"

# or target-driven instructions
npx -y @midscene/ios@1 act --prompt "open Settings and navigate to Wi-Fi, tell me the connected network name"

Assert Current Screen State

Use assert to verify that the current screen satisfies a natural language condition. It does not perform UI actions; it checks the visible screen state and passes only when the assertion is true. Use this for validation, QA checks, and final state verification after act.

npx -y @midscene/ios@1 assert --prompt "there is a login button visible"
npx -y @midscene/ios@1 assert --prompt "the settings screen shows Wi-Fi and Bluetooth options"

By default a failed assertion throws an AI-generated reason. Pass --message to throw a custom error message instead, which is useful for surfacing the intended outcome in QA and CI logs.

npx -y @midscene/ios@1 assert \
  --prompt "the order confirmation screen is visible" \
  --message "the order should be confirmed after tapping Pay"

When the assertion needs to compare against a reference image (icon, logo, screenshot), pass --image for the URL/path and --image-name for its display name. Each --image may be an http(s) link, a data: URI, or a local file path. Repeat both flags in matching order when you need to attach more than one image. Add --convertHttpImage2Base64 true when the model cannot reach the URL directly. Requires @midscene/ios@1.9.0+.

npx -y @midscene/ios@1 assert \
  --prompt "the visible app icon matches the supplied reference image" \
  --image "https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" \
  --image-name "icon" \
  --convertHttpImage2Base64 true

# or with a local file
npx -y @midscene/ios@1 assert \
  --prompt "the header on screen matches the local screenshot" \
  --image "./fixtures/header.png" \
  --image-name "header"

# multiple reference images — pair --image and --image-name by order
npx -y @midscene/ios@1 assert \
  --prompt "the screen shows both the app icon and the header" \
  --image "./fixtures/icon.png"   --image-name "icon" \
  --image "./fixtures/header.png" --image-name "header"

Record and Assert Transient UI

Use a recording when the state to verify may disappear before a current-screen assertion runs, such as a toast, loading banner, animation, or transition:

# Terminal 1: keep this foreground command running
npx -y @midscene/ios@1 record start --device-id <udid> \
  --output ./submission-observation.json

# Terminal 2, while Terminal 1 records
npx -y @midscene/ios@1 act --device-id <udid> \
  --prompt "tap the Submit button"

# Send Ctrl+C to Terminal 1 and wait for the saved-path message, then assert
npx -y @midscene/ios@1 assert --device-id <udid> \