AI-powered mobile device automation for Android and iOS devices, emulators, and simulators
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
tools
-
debug_app
Launch an app in debug mode and write stdout/stderr to a log file
-
execute_dsl
Primary tool. Execute a batch of DSL steps: tap, type, swipe, observe, assertions, web automation, metrics, screen recording, and more.
-
get_device
Get details about a specific device
-
get_screenshot
Fast, low-quality screenshot for LLM visual analysis (may be downscaled; response includes scale factor)
-
install_app
Install an .apk or .ipa from a local file path
-
list_apps
List installed apps on the device
-
list_devices
List all connected Android and iOS devices
-
save_screenshot
Full-quality PNG to disk for reporting, debugging, or sharing
-
start_bridge
Start the automation bridge on a device (required before interaction)
-
stop_bridge
Stop the automation bridge
-
test_get_active
Get the active test project directory and its .mob cases
-
test_list_projects
List all known test project directories with their .mob cases
-
test_run
Run a .mob test case on a device (project_dir + case_path + device_id, optional params for ${name} substitution)
-
uninstall_app
Uninstall an app by bundle ID / package name
filesystem 1
- fs MobAI-App-mobai-mcp-dddf8b4/src/index.ts :17
import * as fs from "fs";
network 1
- net MobAI-App-mobai-mcp-dddf8b4/src/index.ts :101
response = await fetch(url, opts);
install hooks 1
- prepublishOnly MobAI-App-mobai-mcp-dddf8b4/package.json :21
npm run build
declared dependencies 3
- @modelcontextprotocol/sdk@^1.25.3
- @types/node@^20.0.0
- typescript@^5.0.0