iOS Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:

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.

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.

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.

Automate iOS devices using npx @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.

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: Qwen3-VL

MIDSCENE_MODEL_API_KEY="your-openrouter-api-key"
MIDSCENE_MODEL_NAME="qwen/qwen3-vl-235b-a22b-instruct"
MIDSCENE_MODEL_BASE_URL="https://openrouter.ai/api/v1"
MIDSCENE_MODEL_FAMILY="qwen3-vl"

Example: Doubao Seed 1.6

MIDSCENE_MODEL_API_KEY="your-doubao-api-key"
MIDSCENE_MODEL_NAME="doubao-seed-1-6-250615"
MIDSCENE_MODEL_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
MIDSCENE_MODEL_FAMILY="doubao-vision"

Commonly used models: Doubao Seed 1.6, Qwen3-VL, 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 @midscene/ios@1 connect

Take Screenshot

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

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

Disconnect

npx @midscene/ios@1 disconnect

Workflow Pattern

Since CLI commands are stateless between invocations, follow this pattern:

Connect to establish a session
Launch the target app and take screenshot to see the current state, make sure the app is launched and visible on the screen.
Execute action using act to perform the desired action or target-driven instructions.
Disconnect when done

Best Practices

Be specific about UI elements: Instead of vague descriptions, provide clear, specific details. Say "the Settings icon in the top-right corner" instead of "the icon".
Describe locations when possible: Help target elements by describing their position (e.g., "the search icon at the top right", "the third item in the list").
Never run in background: Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.
Batch related operations into a single act command: When performing consecutive operations within the same app, combine them into one act prompt instead of splitting them into separate commands. For example, "open Settings, tap Wi-Fi, and check the connected network" should be a single act call, not three. This reduces round-trips, avoids unnecessary screenshot-analyze cycles, and is significantly faster.
Summarize report files after completion: After finishing the automation task, collect and summarize all report files (screenshots, logs, output files, etc.) for the user. Present a clear summary of what was accomplished, what files were generated, and where they are located, making it easy for the user to review the results.

Example — Alert dialog interaction:

npx @midscene/ios@1 act --prompt "tap the Delete button and confirm in the alert dialog"
npx @midscene/ios@1 take_screenshot

Example — Form interaction:

npx @midscene/ios@1 act --prompt "fill in the username field with 'testuser' and the password field with 'pass123', then tap the Login button"
npx @midscene/ios@1 take_screenshot

Troubleshooting

WebDriverAgent Not Running

Symptom: Connection refused or timeout errors. Solution:

Ensure WebDriverAgent is installed and running on the device.
See https://midscenejs.com/zh/usage-ios.html for setup instructions.

Device Not Found

Symptom: No device detected or connection errors. Solution:

Ensure the device is connected via USB and trusted.

API Key Issues

Symptom: Authentication or model errors. Solution:

Check .env file contains MIDSCENE_MODEL_API_KEY=<your-key>.
See https://midscenejs.com/zh/model-common-config.html for details.