原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Agent Droid Bridge

作者:Neverlow512版本 0.6.1i★ –i在你的电脑上运行
注册名称io.github.Neverlow512/agent-droid-bridge

安装

概览

作者提供的说明(英文原文)

MCP server giving AI agents eyes and hands inside Android devices via ADB

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: ADB_EXECUTION_MODE, ADB_ALLOW_SHELL, ADB_PATH, ADB_EXTRA_TOOL_PACKS, ADB_DENIED_TOOLS, ADB_SHELL_ALLOWLIST, ADB_SHELL_DENYLIST, MCP_LOG_ENABLED, MCP_LOG_DIR, ADB_LOG_LEVEL, ADB_COMMAND_TIMEOUT, ADB_SCREENSHOT_TIMEOUT, ADB_UI_CHANGE_TIMEOUT, ADB_UI_CHANGE_POLL_INTERVAL, ADB_AAPT_TIMEOUT, ADB_CONFIG_SOURCE

你需要

  • PyPI已安装 Python 的 uv(用于 uvx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "agent-droid-bridge": {
      "command": "uvx",
      "args": [
        "agent-droid-bridge"
      ],
      "env": {
        "ADB_EXECUTION_MODE": "your-value",
        "ADB_ALLOW_SHELL": "your-value",
        "ADB_PATH": "your-value",
        "ADB_EXTRA_TOOL_PACKS": "your-value",
        "ADB_DENIED_TOOLS": "your-value",
        "ADB_SHELL_ALLOWLIST": "your-value",
        "ADB_SHELL_DENYLIST": "your-value",
        "MCP_LOG_ENABLED": "your-value",
        "MCP_LOG_DIR": "your-value",
        "ADB_LOG_LEVEL": "your-value",
        "ADB_COMMAND_TIMEOUT": "your-value",
        "ADB_SCREENSHOT_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_POLL_INTERVAL": "your-value",
        "ADB_AAPT_TIMEOUT": "your-value",
        "ADB_CONFIG_SOURCE": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add agent-droid-bridge --env ADB_EXECUTION_MODE=your-value --env ADB_ALLOW_SHELL=your-value --env ADB_PATH=your-value --env ADB_EXTRA_TOOL_PACKS=your-value --env ADB_DENIED_TOOLS=your-value --env ADB_SHELL_ALLOWLIST=your-value --env ADB_SHELL_DENYLIST=your-value --env MCP_LOG_ENABLED=your-value --env MCP_LOG_DIR=your-value --env ADB_LOG_LEVEL=your-value --env ADB_COMMAND_TIMEOUT=your-value --env ADB_SCREENSHOT_TIMEOUT=your-value --env ADB_UI_CHANGE_TIMEOUT=your-value --env ADB_UI_CHANGE_POLL_INTERVAL=your-value --env ADB_AAPT_TIMEOUT=your-value --env ADB_CONFIG_SOURCE=your-value -- uvx agent-droid-bridge

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-droid-bridge": {
      "command": "uvx",
      "args": [
        "agent-droid-bridge"
      ],
      "env": {
        "ADB_EXECUTION_MODE": "your-value",
        "ADB_ALLOW_SHELL": "your-value",
        "ADB_PATH": "your-value",
        "ADB_EXTRA_TOOL_PACKS": "your-value",
        "ADB_DENIED_TOOLS": "your-value",
        "ADB_SHELL_ALLOWLIST": "your-value",
        "ADB_SHELL_DENYLIST": "your-value",
        "MCP_LOG_ENABLED": "your-value",
        "MCP_LOG_DIR": "your-value",
        "ADB_LOG_LEVEL": "your-value",
        "ADB_COMMAND_TIMEOUT": "your-value",
        "ADB_SCREENSHOT_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_POLL_INTERVAL": "your-value",
        "ADB_AAPT_TIMEOUT": "your-value",
        "ADB_CONFIG_SOURCE": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "agent-droid-bridge": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-droid-bridge"
      ],
      "env": {
        "ADB_EXECUTION_MODE": "your-value",
        "ADB_ALLOW_SHELL": "your-value",
        "ADB_PATH": "your-value",
        "ADB_EXTRA_TOOL_PACKS": "your-value",
        "ADB_DENIED_TOOLS": "your-value",
        "ADB_SHELL_ALLOWLIST": "your-value",
        "ADB_SHELL_DENYLIST": "your-value",
        "MCP_LOG_ENABLED": "your-value",
        "MCP_LOG_DIR": "your-value",
        "ADB_LOG_LEVEL": "your-value",
        "ADB_COMMAND_TIMEOUT": "your-value",
        "ADB_SCREENSHOT_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_TIMEOUT": "your-value",
        "ADB_UI_CHANGE_POLL_INTERVAL": "your-value",
        "ADB_AAPT_TIMEOUT": "your-value",
        "ADB_CONFIG_SOURCE": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • ADB_EXECUTION_MODE env
    Security mode. 'unrestricted' allows all shell commands with an optional denylist. 'restricted' allows only commands in ADB_SHELL_ALLOWLIST.
  • ADB_ALLOW_SHELL env
    Set to 'false' to block all adb shell commands regardless of execution mode.
  • ADB_PATH env
    Path to the ADB binary. Use a full path if adb is not on your system PATH.
  • ADB_EXTRA_TOOL_PACKS env
    Comma-separated list of extra tool packs to load. Set to 'app_manager' to enable 9 additional app management tools.
  • ADB_DENIED_TOOLS env
    Comma-separated list of tool names to hide from the agent at startup.
  • ADB_SHELL_ALLOWLIST env
    Comma-separated list of shell commands permitted in restricted mode. Empty blocks all shell commands.
  • ADB_SHELL_DENYLIST env
    Comma-separated list of shell commands blocked in unrestricted mode.
  • MCP_LOG_ENABLED env
    Set to 'true' to enable session logging. Requires MCP_LOG_DIR.
  • MCP_LOG_DIR env
    Absolute path to the directory where session logs are written. Required when MCP_LOG_ENABLED is true.
  • ADB_LOG_LEVEL env
    Server process log level.
  • ADB_COMMAND_TIMEOUT env
    Maximum seconds to wait for any ADB command.
  • ADB_SCREENSHOT_TIMEOUT env
    Maximum seconds to wait for a screenshot capture.
  • ADB_UI_CHANGE_TIMEOUT env
    Default timeout in seconds for detect_ui_change.
  • ADB_UI_CHANGE_POLL_INTERVAL env
    How often in seconds detect_ui_change polls the UI hierarchy.
  • ADB_AAPT_TIMEOUT env
    Maximum seconds to wait for aapt dump badging, used by the app_manager pack.
  • ADB_CONFIG_SOURCE env
    Set to 'yaml' to load configuration from adb_config.yaml instead of environment variables.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Neverlow512 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32568 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32568 个服务器的 7% 更新
  • 基础检查结果等于或优于此分类中其他 32568 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Agent Droid Bridge 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.6.1)于7个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, FlyDocs

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

FlyDocs

作者:flydocs.ai

Spec-driven development workflow: your agent works issues, sessions and the status lifecycle.

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Agent Droid Bridge

Agent Droid Bridge is an MCP server that connects AI agents to Android devices and emulators over ADB. It is built for mobile automation, app testing, dynamic analysis, and reverse engineering: exposing the full surface of ADB as structured tools that any MCP-compatible AI client can call directly. If ADB can do it, an agent can do it.


Purpose-built tools return structured, minimal responses. No raw XML dumps, no wasted context — agents stay fast across long sessions.

Demo

The demo above runs through a few straightforward tasks to show what a connected agent can do, and this is just scratching the surface:

  • Installs the Paint app, opens it, and draws a house by calculating pixel coordinates for the walls and roof
  • Opens the device browser, searches for "MCP Wikipedia", navigates to the result page, and takes a screenshot
  • Opens the Calculator, computes 1337 × 42, and extracts the result to the host machine
  • Opens Contacts, creates a new entry with a name and phone number, and confirms it saved
  • Opens the Calendar and schedules an appointment for a specific date
  • Opens Settings and toggles dark mode
  • Extracts the Calculator APK from the device to the host machine
  • Installs Notepad, writes a one-sentence summary of every task completed, and takes a final screenshot

What it does

Tools

  • 14 built-in tools for screen capture, UI inspection, text reading, element extraction, touch and swipe input, text entry, keycode events, app launching, ADB commands, and device inspection
  • app_manager pack adds 9 tools for package management, app lifecycle, APK extraction, permissions, and intent injection. Load it with ADB_EXTRA_TOOL_PACKS=app_manager
  • Tool availability is reflected in the server's startup instructions. Agents receive an accurate catalog at connect time

Device handling

  • Auto-detects a single connected device; prompts for selection when multiple devices are present
  • Runs over stdio, compatible with any MCP-capable AI client
  • Structured responses instead of raw XML dumps, keeping agent context lean across long automation runs

Security

  • Two execution modes: unrestricted (full ADB access, optional denylist) and restricted (allowlist-only, blocks everything not explicitly permitted)
  • Set ADB_ALLOW_SHELL=false to disable all shell commands regardless of mode
  • Hide specific tools from the agent with ADB_DENIED_TOOLS
  • All commands parsed via shlex. No shell injection possible

Observability

  • Optional session recorder logs every tool call, ADB command, and security event to structured JSONL files. Enable with MCP_LOG_ENABLED=true and MCP_LOG_DIR

Use cases

Mobile QA and test automation Automate UI flows across real devices and emulators without modifying the app or writing test code. Tap, swipe, type, read screen content, take screenshots — all from a natural language prompt.

App security research Extract APKs, inspect declared permissions, fire arbitrary intents, and observe runtime behavior on screen. No instrumentation, no jailbreak required.

Dynamic analysis Launch apps in controlled states, drive UI interactions, capture screen state at each step, and pull artifacts — all scriptable through an AI agent.

Development and debugging Install builds, verify UI states, check app info, and run ADB commands without leaving your coding environment.

Install

uvx agent-droid-bridge

No cloning or virtual environments needed. Requires Python 3.11+ and ADB installed on your host.

uvx is provided by uv. If you don't have it: curl -LsSf https://astral.sh/uv/install.sh | sh

To install from source instead, see docs/setup.md — Option B.

To verify the install: uvx agent-droid-bridge --help

Quick start

  1. Install ADB — see docs/setup.md for platform-specific instructions
  2. Connect an Android device or start an emulator
  3. Add the server to your MCP client config:
{

"mcpServers": { "agent-droid-bridge": { "command": "uvx", "args": ["agent-droid-bridge"], "env": { "ADB_EXECUTION_MODE": "unrestricted", "ADB_ALLOW_SHELL": "true", "ADB_PATH": "adb", "ADB_EXTRA_TOOL_PACKS": "", "MCP_LOG_ENABLED": "false", "MCP_LOG_DIR": "~/logs/agent-droid-bridge" } } } }

To enable session logging, set MCP_LOG_ENABLED to "true" and update MCP_LOG_DIR to a writable path on your machine.

VariableDefaultDescription
ADB_EXECUTION_MODEunrestrictedSecurity mode. unrestricted allows all shell commands (with optional denylist); restricted allows only commands in ADB_SHELL_ALLOWLIST.
ADB_ALLOW_SHELLtrueSet to false to block all adb shell commands regardless of execution mode.
ADB_PATHadbPath to the ADB binary. Replace with a full path if adb is not on your system PATH (e.g. C:\platform-tools\adb.exe on Windows).
ADB_EXTRA_TOOL_PACKS*(empty)*Comma-separated list of extra tool packs to load. Set to app_manager to enable 9 additional app management tools.
MCP_LOG_ENABLEDfalseSet to true to enable session logging. Requires MCP_LOG_DIR.
MCP_LOG_DIR*(none)*Directory where session logs are written. Required when MCP_LOG_ENABLED is true.
  1. Prompt your agent to use the agent-droid-bridge MCP tools

Full setup guide and environment variable reference: docs/setup.md

Tools

ToolWhat it does
get_ui_hierarchyReturns the current screen as an XML UI hierarchy
take_screenshotCaptures the screen as a base64-encoded PNG
tap_screenSends a tap gesture at pixel coordinates
swipe_screenSends a swipe gesture between two points over a given duration
type_textTypes text into the focused input field
press_keySends an Android keycode event (Back, Home, Enter, etc.)
launch_appLaunches an app by its package/activity component name
execute_adb_commandRuns an arbitrary ADB or ADB shell command
list_devicesLists all Android devices currently visible to ADB with their serial, state, and model
snapshot_uiTakes a lightweight UI snapshot and returns a token for use with detect_ui_change
detect_ui_changePolls for a UI change after an action; accepts a snapshot token as baseline; returns hierarchy only when requested
get_screen_elementsParses the UI hierarchy and returns structured elements with coordinates and interaction properties; supports tappable, interactive, input, and all modes
get_screen_textReturns all visible text on screen sorted top-to-bottom, as plain text
check_device_capabilitiesReturns structured device information — identity, security posture, and hardware specs — in a single call; supports identity, security, hardware, and all modes
Extra tool packs

Optional packs extend the core toolset. Enable them by setting ADB_EXTRA_TOOL_PACKS in your MCP client config. See docs/extra-tool-packs.md.

app_manager

Package management, app lifecycle control, APK extraction, permission management, and intent injection.

ToolWhat it does
list_packagesLists installed packages with optional filtering, search, and detail levels
get_app_infoReturns full static metadata for a single installed app
install_appInstalls an APK from a host path onto the device
uninstall_appRemoves an installed app by package name
pull_apkExtracts the installed APK from the device to the host
manage_permissionGrants, revokes, checks, or lists runtime permissions for an app
launch_app_extraLaunches an app by package name, auto-resolving the launcher activity
manage_appControls app runtime state — stop, clear data, clear cache, enable, disable
inject_intentFires an intent at a component via am start, am broadcast, or am startservice

Full parameter reference: docs/tools.md

Configuration

Configure the server entirely from your MCP client's env block. No files to edit. The env block in the Quick Start above covers the most common settings. For the full reference including security filtering, tool visibility, and timeouts, see docs/configuration.md.

To use a YAML config file instead, set ADB_CONFIG_SOURCE=yaml. See docs/configuration.md for details.

Session recording is separate. Enable it with MCP_LOG_ENABLED=true and MCP_LOG_DIR. Full reference: [doc

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx