admcp - Android Debug MCP

io.github.dima-xd由 GitHub 帳號 dima-xd 發布v1.0.0更新於 Nov 1, 2026

Local-first MCP server for Android debugging via ADB, JDI, LLDB, and Flutter.

已驗證STDIO僅桌面瀏覽器自動化開發者工具

概覽

AI 產生的概覽

本機 MCP 伺服器,讓 AI 助理透過 ADB、JDI、LLDB 與 Flutter 在實機或模擬器上檢視、操作並偵錯 Android 應用程式。

可以做什麼
  • 列出並檢視裝置、探測工具鏈、開啟與描述工作區
  • 建置、安裝並啟動應用程式,管理偵錯工作階段
  • 檢視 UI 與 Compose 無障礙樹,尋找元素、點擊操作並截圖
  • 啟動、查詢、停止並統計 logcat,包含當機訊號
  • 連接 Java/Kotlin JDI、原生 LLDB 或 Flutter DAP 偵錯器,設定中斷點、單步執行、查看呼叫堆疊、變數與暫存器並求值運算式
  • 擷取 Perfetto 追蹤與堆積傾印,取得、預覽並分析產出物與診斷資訊
適用情境
適合讓代理在已連接的 Android 實機或模擬器上重現問題、驗證介面變更、讀取當機記錄或單步偵錯,而不必由人在 Android Studio 中逐步點擊。鎖定 Android 開發者、代理建構者,以及需要可重現裝置證據的 QA 流程。
執行需求
以本機程序執行於 Windows、Linux 或 macOS,需要 JDK 21 與 Android SDK platform-tools(adb);多數工具還需連接裝置或模擬器。Flutter SDK、NDK 的 lldb/lldb-server 與 lldb-dap 為選用。透過 --platform-tools、--artifacts、--trust-workspace 等命令列選項設定。不需雲端帳號或 API 金鑰。
安裝前請注意
它會操作真實裝置:介面操作、安裝與啟動應用程式都會改變裝置狀態,破壞性介面操作需要主機確認或一次性權杖。專案控制的程式碼只有在啟動時明確授予工作區信任後才會執行。僅支援可偵錯的開發版本,root 與安全性繞過不在範圍內。產出物讀取預設限制在儲存根目錄內並會截斷與去識別化;伺服器以本機為優先,不會上傳專案或裝置資料。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 admcp - Android Debug MCP,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

admcp

[admcp - Android debugging for AI agents]

admcp is a local-first Model Context Protocol (MCP) server for Android development. It connects any MCP stdio client to a real device or emulator and exposes 51 typed tools for UI inspection, screenshots, logcat, Java/Kotlin JDI debugging, native LLDB, Flutter/Dart DAP, Compose inspection, Perfetto traces, heap dumps, artifacts and evidence-based diagnostics.

No root. No cloud account required.

[MCP] [Android] [JDK] [Tools] [License]

Quick start | What it can do | Example prompts | Why admcp | Documentation

Status: v1, 51 tools, live-tested on a OnePlus CPH2747 (API 36, arm64-v8a). Full evidence and remaining limits: implementation status.

Quick start

  1. Install JDK 21 and Android SDK platform-tools (adb).
  2. Download admcp-<version>.zip from GitHub Releases and unzip it. MCPB-compatible clients can install admcp-<version>.mcpb from the same release instead.
  3. Point your MCP client at bin/admcp.bat on Windows or bin/admcp on Linux and macOS.

Any MCP stdio client can use it. The JSON below uses the common mcpServers shape; adapt the command and arguments to your client (Claude Code, Cursor, VS Code, Codex, Gemini CLI, and similar).

json
{  "mcpServers": {    "admcp": {      "command": "C:\\Tools\\admcp\\admcp-<version>\\bin\\admcp.bat",      "args": [        "--platform-tools", "C:\\Android\\Sdk\\platform-tools",        "--artifacts", "C:\\temp\\admcp-artifacts"      ]    }  }}

On Linux and macOS, use /opt/admcp/admcp-<version>/bin/admcp as command.

Verify the install:

bat
C:\Tools\admcp\admcp-<version>\bin\admcp.bat --selftest

On Linux and macOS:

sh
/opt/admcp/admcp-<version>/bin/admcp --selftest

You should see catalog=51 registered=51 version=<version> on stderr. The server then speaks MCP over stdio; stdout is reserved for protocol traffic.

What it can do

AreaTools
Device and workspacedevice_list, device_inspect, toolchain_probe, workspace_open, workspace_describe
App lifecycleapp_build, app_install, app_launch
Sessionssession_start, session_status, session_stop
UI and screenshotsui_inspect, ui_find, ui_act, ui_screenshot, compose_inspect
Logslogcat_start, logcat_query, logcat_stop, logcat_statistics, logcat_health
Java/Kotlin debugdebug_attach, breakpoints, debug_step, debug_stack, debug_variables, debug_evaluate
Native debugLLDB attach, breakpoints, stack, registers, memory reads and modules
Flutter debugDART_DAP attach, breakpoints, stack, variables, step, pause and detach
PerformancePerfetto system traces, heap dumps and performance_trace_analyze
Artifacts and evidenceartifact_get, analyze_artifact, previews, diagnostics_* and signals_crashes

The full 51-tool contract is in docs/architecture/mcp-tool-catalog-v1.md. The catalog is validated by contract tests.

Example prompts

Once admcp is connected, ask your agent things like:

text
Inspect the current screen, find the INCREMENT button, tap it, and verify the counter changed.Start logcat, reproduce the crash, then summarize the stack trace and the last 50 lines before it.Launch the app, attach JDI, set a breakpoint in MainActivity, and show locals when it hits.Inspect this Compose screen and tell me which accessibility node is the DELETE COUNTER button.Record a 5-second Perfetto trace and summarize what happened.Attach LLDB to the native library, break in fixture_increment, and show the registers.

Why admcp

Many Android MCP tools are thin command wrappers. admcp keeps device, workspace, process and session state together, then exposes debugging primitives with typed schemas, artifacts and safety gates.

It is for:

  • Android developers who want Claude Code, Cursor or another agent to inspect and debug a real device.
  • Agent builders who need stable, typed Android actions instead of parsing adb strings.
  • QA and automation workflows that need reproducible evidence from a device.
adb and shell scriptsAndroid Studioadmcp
Built for AI agentsNoNoYes
Typed MCP tool schemasNoNo51 tools
Session, process and backend stateNoPartialYes
JDI, LLDB and Flutter over MCPNoHuman UIYes
Evidence, artifacts and diagnosticsNoPartialYes
Local-first, no cloud accountYesYesYes

Android Studio is the better tool for a human sitting at the IDE. admcp is for the agent that needs to inspect, act and debug without a human driving every click.

How it works

mermaid
flowchart LR    Client["MCP client / agent"] -->|stdio| Server["admcp (MCP server)"]    Server --> ADB["ADB / Android CLI"]    Server --> JDI["JDI (JDWP client)"]    Server --> LLDB["lldb-dap"]    Server --> DAP["Flutter DAP"]    ADB --> Device["Android device / emulator"]    JDI -.->|via adb forward| ADB    LLDB -.->|via adb forward / lldb-server| ADB    DAP -.->|via adb forward| ADB

The server runs on your machine next to the Android toolchain. It does not upload your project or device data anywhere.

Verified

  • 186 tests with 0 failures on the verified host.
  • The catalog registers all 51 tools over MCP stdio.
  • Live device: OnePlus CPH2747, API 36, arm64-v8a.
  • JDI: attach, breakpoints, step, stack, locals and read-only evaluation.
  • LLDB: attach, breakpoints, stack, registers, bounded memory reads and modules.
  • Flutter: DART_DAP breakpoints, stack, variables, step, pause and detach.
  • Compose: accessibility-tree inspection and verified UI actions.
  • Performance: Perfetto capture/analysis and HPROF heap-dump capture.
  • Evidence: logcat, crash buffer, artifacts, session timeline and diagnostics.

Device-dependent integration tests skip when no device is attached. See implementation status for the full acceptance evidence.

Requirements

  • JDK 21.
  • Android SDK platform-tools (adb).
  • Windows, Linux or macOS.
  • Optional: Android CLI, Flutter SDK, NDK lldb/lldb-server, lldb-dap and a connected device or emulator.

Only debuggable developer builds are supported. Root and Android security bypasses are out of scope.

Build from source

Build, test and package from source

The Gradle wrapper is checked in; no local Gradle install is required.

Windows:

bat
gradlew.bat clean testgradlew.bat :app:admcp:installDist

Linux and macOS:

sh
./gradlew clean test./gradlew :app:admcp:installDist

The installable distribution is written to app/admcp/build/install/admcp/. The release archive is built with :app:admcp:distZip and written to app/admcp/build/distributions/admcp-<version>.zip.

Releases are automated with semantic-release from Conventional Commits on pushes to main or master: fix: is a patch release, feat: is a minor release and BREAKING CHANGE: is a major release. No release PR or changelog is generated.

Configuration

OptionPurpose
--platform-tools <dir>Directory containing adb
--workspace <dir>Default workspace root
--android-cli <path>Android CLI executable
--flutter-root <dir>Flutter SDK root
--artifacts <dir>Artifact store root
--trust-workspace <dir>Operator-approved workspace root; repeatable
--selftestPrint catalog/registration counts and exit
--versionPrint the version and exit

workspace_trust only succeeds for a canonical root passed to the server at startup with --trust-workspace. A tool argument cannot self-assert approval.

Known limitations

  • The verified device is a OnePlus CPH2747 on API 36; other OEM, API and transport combinations are not claimed.
  • Simultaneous JDI and LLDB inspection is not reliable on the verified device. Sequential switching works with debug_attach(switchBackend=true).
  • Compose TREE uses the accessibility hierarchy. Internal semantics, slot table and recomposition data require app instrumentation.
  • No host trace_processor_shell is bundled, so trace analysis returns a bounded summary unless Perfetto SQL tooling is installed.
  • Crashlytics issue clusters require android auth login; the local crash buffer remains the default evidence source.
  • Native LLDB needs a separately installed lldb-dap and an ABI-matched lldb-server.
  • The host confirmation dialog requires an interactive desktop. Headless servers fail closed to a one-shot token.

See implementation status for details and exact error behavior.

Security

  • Only debuggable developer builds are supported.
  • Project-controlled code runs only after an explicit workspace trust grant.
  • Destructive UI actions require host confirmation or a one-shot token bound to the session and action.
  • Artifact reads are confined to the store root, capped and redacted by default.
  • The server is local-first: no cloud account is required.

Documentation

Contributing

Issues and pull requests are welcome. The public tool catalog is versioned; open an issue before adding or renaming a public tool. Run gradlew test before sending a PR.

If admcp saves your agent time, a star helps more Android developers find it.

License

Apache License 2.0. See LICENSE.

來源:README.md,提交 94e5006

工具

0
SourceWeft 曾在隔離沙箱中以無憑證方式啟動該軟體包一次,以列出其工具,但未能完成:該軟體包類型無法在沙箱中執行。

版本歷史

1
  1. v1.0.0最新Nov 1, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分