$ loading_
Control Android devices via ADB for UI interaction and inspection.
This is an open-source MIT-licensed MCP server for controlling Android devices via ADB, with no required secrets and no stated remote endpoints; no explicit high-risk red flags are evident from the provided material. Its core capability is local ADB-based execution and device control/inspection, which warrants caution due to strong system and device interaction privileges.
The material explicitly states that no keys or environment variables are required, and no API tokens, account passwords, or cloud credentials are mentioned, so credential exposure risk appears low.
Neither the material nor the objective checks declare remote endpoints; the description only mentions controlling Android devices via ADB, with no evidence of sending user data to third-party services.
The system checks mark it as executes-code, and its functionality depends on invoking ADB locally for screen interaction and UI inspection. This is a common but powerful local execution capability for an MCP tool, so care is needed because it can issue operational commands to connected devices.
By description, it can at least access Android device UI state and interaction channels, potentially including UI hierarchy, screenshots/screen content, and input actions. The material does not show extra local file or system data permissions beyond the stated purpose, but visibility into device-side data should be assessed carefully.
It has an open-source repository and an MIT license, making the code theoretically auditable, which is a clear risk-reducing factor; however, it comes from a third-party registry, has 0 stars, and an unknown maintenance status, so evidence of trust and maturity is limited.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "agentic-android" yet — see the docs or source repo.
Connect to my Android test device, open the target app, tap Login, navigate to the Settings page, and check whether the options “Notifications” and “Privacy” appear. Then output the test steps and results.
An Android UI test result including executed steps, UI inspection findings, and any exceptions.
Read the current Android screen UI hierarchy, list all clickable elements with their text, resource IDs, and coordinates, and identify the most likely primary action button.
A structured list of current screen UI elements and the identified primary action button.
Starting from the home screen on the Android device, complete a checkout flow: search for a product, add it to the cart, and go to the checkout page. Record the UI state at each step and explain where it gets stuck if it fails.
A step-by-step execution report of the user flow for bug reproduction or feature validation.
Automate Android devices via ADB for testing, control, and task execution.
Control Android devices with natural language for UI and system automation.
Remotely control Android devices via ADB for debugging, testing, and management.
Automate Android UI interactions, snapshots, and gesture recording through MCP.
Control multiple iOS and Android devices for testing, screenshots, and UI actions.
Control Android devices through AI for testing, debugging, and automation.