Claude Mobile
mcp-devices 4.0.0(前身为claude-in-mobile)
👉 想要一个包搞定所有?继续使用
claude-in-mobile。对你来说什么都没有改变。 安装方式相同,所有平台打包在一起,仍然得到维护:
npm i -g claude-in-mobile就是这样——一体化版本。仅当你希望单独安装各个平台时才继续阅读(这正是
mcp-devices的用途)。
Related MCP server: Android MCP Server
两个版本——同一工具
版本 | 适用于 | 安装 |
| 想要一站式,零配置 |
|
| 想要精简基础 + 仅安装你需要的平台 |
|
两者都得到维护。claude-in-mobile 在 4.0 中更名为 mcp-devices 并拆分为模块化版本;一体化版本保持其名称和不变的安装方式。本 README 的其余部分涵盖模块化 mcp-devices 版本。
3 步安装(模块化)
# 1. base server
npm i -g mcp-devices
# 2. add a platform (example: Android)
npm i -g @mcp-devices/plugin-android
mcp-devices install android
# 3. point your MCP client at it
# { "mcpServers": { "mobile": { "command": "mcp-devices" } } }重启你的 MCP 客户端。完成——让 Claude “给我的 Android 设备截个图”,它就能工作。
随时检查先决条件:mcp-devices doctor。
选择你的平台
每个平台是一个独立的包。安装你需要的平台——完整指南参见各文档:
平台 | 安装 | 需要 | 指南 |
Android |
|
| |
iOS |
|
| |
Web |
| Chrome | |
Desktop |
| Java/JDK | |
Aurora |
|
| |
All |
| — | — |
安装包后,启用它:mcp-devices install <name>(或 all),然后重启。
它能做什么
驱动应用 — 截图、点击/滑动/输入、启动应用、UI 树、Shell、日志、权限、文件。
调试实时应用 — 断点、单步执行、检查变量、求值表达式(Android JDWP + iOS LLDB)。参见调试 »。
测试 — 视觉回归、无障碍审计、性能、传感器/网络模拟。
这些功能以约 20 个内置工具模块和按需调试插件的形式提供——完整工具目录 »。
从一体化切换到模块化?
对打包的 claude-in-mobile 满意吗?什么也不做——它仍然得到维护,安装方式与之前完全一样。本部分仅适用于你想要迁移到精简的模块化版本。
无论如何,你的
claude-in-mobile命令都能继续工作——mcp-devices会同时安装mcp-devices和claude-in-mobile二进制文件。唯一的区别是平台不再打包在一起——安装你实际使用的平台:
npm i -g mcp-devices
npm i -g @mcp-devices/plugin-android # (or plugin-all for everything)
mcp-devices install android工具、操作和 MCP 客户端配置与打包版本相同。
文档
注意事项
模块化基础版本默认不加载任何平台——你需要启用你需要的平台(
mcp-devices install <name>)。claude-in-mobile版本会启用所有平台。调试插件尚未成为
mcp-devices install的一部分——通过MCP_DEVICES_TOOL_PLUGINS=debug或~/.mcp-devices/config.json启用它。更喜欢一个包搞定所有?使用一体化
claude-in-mobile版本(npm i -g claude-in-mobile)——仍然维护,安装方式不变。
Available Tools
14 toolsappC
App lifecycle: launch, stop, install, list
Inputs: action (required), path, delayMs, package, +3 more.
deviceA
Device management + module loading. list/set/set_target/get_target: devices. enable_module/disable_module/list_modules: load browser/desktop/store tools on demand.
Inputs: action (required), module, target, category, +2 more.
flowA
Flow orchestration: batch (multi-command), run (multi-step automation with loops/conditionals), parallel (same action on multiple devices). Use turbo:true for rich feedback (experimental).
Inputs: action (required), args, steps, turbo, +5 more.
inputC
Input actions. tap/double_tap/long_press: coords or text/id/label/index. swipe: direction or coords. text: type text. key: press key.
Inputs: action (required), x, y, x1, +15 more.
repl_expectB
Block until a prompt regex matches, the session idles, the child exits, or the timeout fires.
Inputs: id (required), regex, idleMs, timeoutMs.
repl_keyA
Send a control key (enter/ctrl-c/ctrl-d/tab/arrows) to a session.
Inputs: id (required), key (required).
repl_killA
Terminate a REPL session (SIGTERM, then SIGKILL).
Inputs: id (required).
repl_listB
List active REPL sessions and their statuses.
Inputs: no named parameters.
repl_sendB
Write text to a REPL session. Appends a newline by default.
Inputs: id (required), text (required), newline.
repl_snapshotB
Read the current emulated terminal screen for a session. Output is redacted for common secret patterns unless disabled at plugin construction time.
Inputs: id (required), tail.
repl_spawnA
Start an interactive REPL or CLI process under a PTY. Returns the session id. cmd is exec'd directly (argv split, no shell): env-var prefixes, redirections (2>&1), pipes and globs are NOT interpreted — pass env via the env param, or set shell:true to run cmd through /bin/sh -c.
Inputs: id (required), cmd (required), cwd, env, +4 more.
screenB
Screen capture and annotation. capture: screenshot with compression/diff. annotate: screenshot with element bounding boxes.
Inputs: action (required), diff, preset, quality, +8 more.
systemC
System operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer.
Inputs: action (required), ms, tag, url, +10 more.
uiB
UI inspection and interaction. tree: accessibility tree. find: search elements. find_tap: fuzzy tap (Android). tap_text: tap by text (Desktop). analyze: screen analysis. wait/assert_visible/assert_gone: element checks.
Inputs: action (required), pid, text, fresh, +16 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Most tools have clear, distinct purposes (input vs. screen vs. ui vs. app lifecycle). However, 'input' and 'ui' both handle taps/texts, which could cause confusion; 'repl_*' tools are clearly separate but 'repl_spawn' vs 'repl_send' might overlap slightly in purpose.
Tools mostly follow single-word or verb_noun patterns, with 'repl_*' prefix consistently used. However, mixed styles like 'tap_text' vs 'find_tap' and 'repl_spawn' vs 'spawn' deviation from a uniform convention, though the naming is generally predictable.
14 tools is within the ideal 3-15 range, slightly on the higher end but each covers a distinct functionality area. The count feels appropriate for a mobile automation server, though some categories could be consolidated.
The tool surface covers core mobile automation needs: input, UI inspection, app lifecycle, device management, screen capture, and flow orchestration. Missing are some advanced operations like gesture composition or multi-touch, and the 'system' category is broad but shallow. Overall, no critical gaps for basic workflows.
Maintenance
Related MCP Connectors
Let AI agents control Android and iOS devices on Mobilerun Cloud: screen, input, apps, workflows.
Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. 290+ tools across device control, app management, automation sessions, browser automation, and flow recording / replay. Bearer-auth — get a token at robotactions.com → Profile → API Tokens.
Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs.
Let your AI agent control real iPhones: screenshots, tap, swipe, type and open apps.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI agents to interact with Android devices through UI manipulation, screen capture, touch gestures, text input, and app management via ADB. Provides comprehensive mobile automation capabilities including element detection, navigation, and application control for Android device testing and interaction.9123 PyPI2-
- AlicenseBqualityDmaintenanceEnables control of Android devices via ADB, allowing screenshot capture, touch simulation, and swipe gestures through natural language commands.226MIT
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Android devices and emulators through ADB, allowing control actions like tapping, text input, screenshots, UI inspection, and app launching through natural language.8-
- AlicenseAqualityBmaintenanceEnables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.65 npmMIT