🇺🇸English

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 @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 @midscene/ios@1 connect

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 @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 @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:

1. Connect to establish a session
2. Launch the target app and take screenshot to see the current state, make sure the app is launched and visible on the screen.
3. Execute action using act to perform the desired action or target-driven instructions.
4. Disconnect when done
5. Report results — summarize what was accomplished, present key findings and data extracted during the task, and list any generated files (screenshots, logs, etc.) with their paths

Best Practices

1. 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".
2. 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").
3. Never run in background : Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.
4. Batch related operations into a singleact 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.

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/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.

Weekly Installs

422

Repository

web-infra-dev/m…e-skills

GitHub Stars

137

First Seen

Mar 6, 2026

Security Audits

Gen Agent Trust HubPassSocketPassSnykFail

Installed on

openclaw262

codex199

cursor197

opencode197

cline195

gemini-cli194