Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ADB Pilot: Android Control for MCP Agents

    1

    Give your AI agent safe, structured control of Android devices and emulators over MCP — screenshots, logcat, installs, and UI taps behind approval gates.

    Free

    1 useSecurity scanned
    ADB Pilot: Android Control for MCP Agents

    ADB Pilot: Android Control for MCP Agents

    Example session with this skill installed

    I'm building a mobile app and I want my agent to verify it on the emulator instead of me typing adb commands all day. Repo is at ~/projects/mobile-app, the debug build is /tmp/app-debug.apk, and emulator-5554 is running. Help me configure an ADB Pilot MCP server for Cursor using stdio transport, show which safety layers to enable before I expose shell access, then walk me through a crash-triage run: start com.acme.mobile, capture ten seconds of logcat, and summarize the failure.

    • Read your context and instructions
    • Compiled the adb pilot

    Summary

    ADB Pilot is now wired into Cursor over stdio with the approval-gating policy enabled. The crash-triage run on emulator-5554 reproduced the failure and pinpointed a null cart session in PaymentFragment.onResume().

    CheckBeforeAfter
    ADB accessmanual adb typingadb-pilot --transport stdio in mcp.json
    Device targetingguessed device namesserial emulator-5554 required per call
    Risk gatingnonereboot / uninstall / clear-data approval-gated
    Crash causeunknownNPE at PaymentFragment.kt:87, logged 14:32:07
    FATAL EXCEPTION: main
    java.lang.NullPointerException: getSession(...) must not be null
      at com.acme.mobile.PaymentFragment.onResume(PaymentFragment.kt:87)
    

    Next steps

    • Guard CartRepository.session in onResume with a recreate-or-return path, then reinstall /tmp/app-debug.apk
    • Add the default denylist (/system, /vendor, su, raw pm writes) before enabling the shell tool
    • Re-run the UI smoke-test recipe to confirm the payment screen renders after the fix
    • Keep one clean emulator profile reserved for regression runs
    in mcp.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Controlling Android devices via AI agents often results in flaky execution or dangerous shell access. ADB Pilot provides a structured bridge using the Model Context Protocol (MCP) to give agents safe, granular control over physical devices and emulators. It replaces raw terminal commands with typed tools for UI automation, diagnostic retrieval, and app management.

    What it does

    • Device Management discovers connected hardware, identifies serials, and monitors connection health.
    • UI Automation executes precise taps, swipes, and text input using coordinate or hierarchy-based targeting.
    • Diagnostic Capture retrieves logcat streams, crash reports, ANR files, and memory dumps for triage.
    • App Operations handles APK installation, permission grants, and application lifecycle management.
    • File Transfer manages file round-trips between the host machine and device storage paths.
    • Visual Verification captures screenshots and screen recordings to verify agent actions.

    How it works

    1. Bridge Setup involves connecting a device via USB or TCP/IP and starting the MCP server on the host.
    2. Tool Invocation allows the agent to call specific functions like install_apk or tap_ui through the MCP client.
    3. Safety Gating enforces a risk-based approval model, requiring human confirmation for destructive actions like reboots or deletions.
    4. Result Normalization converts raw ADB output into structured JSON for the agent to process.

    Frameworks & tools

    This skill utilizes the Model Context Protocol (MCP), Android Debug Bridge (ADB), and Python. It supports local execution via stdio or remote access through SSE/HTTP transports.

    Why this beats prompting it yourself

    Writing raw ADB shell commands through an LLM is error-prone and lacks safety boundaries. This skill provides a schema-validated interface that prevents shell injection, enforces device targeting, and categorizes operations by risk level.

    Use cases

    • Automate UI smoke tests on physical devices during CI/CD cycles.
    • Triage application crashes by automatically pulling logs and screen states.
    • Manage large emulator fleets for parallel app testing and data collection.
    • Perform remote device surveys to verify hardware specs and battery health.

    Known limitations

    Requires ADB to be pre-installed and available on the system PATH. Containerized deployment requires complex host USB mapping. Destructive operations on system partitions are blocked by default.

    It is the bridge design and operations blueprint, not a prebuilt server — you supply or install an ADB-over-MCP implementation yourself. Docker-mode ADB still needs host USB access, which is fiddly on some platforms.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Read Files
    Write Files

    File Scopes

    *.json
    *.apk
    *.log
    *.png

    Shell access runs scoped ADB commands against devices you own; file read/write covers MCP client configs, logs, and screenshot artifacts, with no network exposure required.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    ADB Pilot acts as a secure intermediary that translates AI requests into structured ADB commands, preventing the 'hallucinated' shell syntax and security risks common when agents have direct terminal access.

    This skill is compatible with any agent or IDE that supports the Model Context Protocol (MCP), including Claude Desktop, various IDE plugins, and custom Python-based agents.

    Yes, ADB Pilot supports both physical Android devices connected via USB/Wi-Fi and virtual devices running through the Android Studio Emulator or Genymotion.

    You receive the full MCP server package, including the tool schemas for UI automation and diagnostics, along with a setup guide to link your local ADB environment to your agent.

    Safety is managed via an approval gate system that flags high-risk tools like device reboots or file deletions for human confirmation before execution.

    You must have the Android SDK Platform-Tools (ADB) installed on your host machine and available in your system PATH for the MCP server to communicate with your devices.

    New in Mobile Development