Canlah Skills Radar
Hephaestus · 页面优化工程师

Claude Mobile

alexgladkov/claude-in-mobile
✓ I/O · 14认领这个员工

Enables automation of Android devices and iOS simulators through a unified API. Supports device listing, screenshots with automatic compression for LLM processing, tap and swipe gestures by coordinates or element text, text input, app launching and installation, UI hierarchy inspection, device logs retrieval, and shell command execution. Provides cross-platform device control for mobile testing and debugging workflows.

该 server 含写操作工具 (repl_send) — 接入你自己的账号前,先确认它的授权范围。

真实 I/O · 已连通 ✓

启动 server · tools/list · 14 个工具 · claude-mobile

下面每个工具的字段、类型、必填项,都是我们真的把 server 启动、tools/list 拉回来的原始 JSON Schema —— 真实的工具契约。注意:下方「示例调用」是按 schema 自动生成的演示,不是真实调用的返回。

device

Device management + module loading. list/set/set_target/get_target: devices. enable_module/disable_module/list_modules: load browser/desktop/store tools on demand.

Input(真实 schema)
actionstringrequired
deviceIdstring
Device ID (for set)
platformstring
Filter by platform or target platform
targetstring
Target platform to switch to (for set_target)
moduleany
Module name or array of names (for enable_module/disable_module)
categorystring
Enable/disable all modules in category (for enable_module/disable_module)
示例调用
{
  "tool": "device",
  "arguments": {
    "action": "list"
  }
}
screen

Screen capture and annotation. capture: screenshot with compression/diff. annotate: screenshot with element bounding boxes.

Input(真实 schema)
actionstringrequired
platformstring
Target platform. If not specified, uses the active target.
presetstring
Quality preset: low (270x480 q40), medium (540x960 q55, default), high (810x1440 q70)
compressboolean
Compress image (default: true)
maxWidthnumber
Max width in pixels (default: 540)
maxHeightnumber
Max height in pixels (default: 960)
qualitynumber
JPEG quality 1-100 (default: 55)
monitorIndexnumber
Monitor index for multi-monitor desktop setups
diffboolean
Compare with previous screenshot (capture only)
diffThresholdnumber
Pixel difference threshold 0-255 (default: 30)
waitForStableboolean
Wait for UI to stabilize before capturing (capture only)
deviceIdstring
Target device ID for multi-device. If omitted, uses active device.
示例调用
{
  "tool": "screen",
  "arguments": {
    "action": "capture"
  }
}
input

Input actions. tap/double_tap/long_press: coords or text/id/label/index. swipe: direction or coords. text: type text. key: press key.

Input(真实 schema)
actionstringrequired
xnumber
X coordinate
ynumber
Y coordinate
x1number
Start X (for custom swipe)
y1number
Start Y (for custom swipe)
x2number
End X (for custom swipe)
y2number
End Y (for custom swipe)
textstring
Element text (tap) or text to type (text action)
resourceIdstring
Find element by resource ID (Android only)
labelstring
iOS only: Accessibility label
indexnumber
Tap element by index from ui_tree output (Android only)
keystring
Key name: BACK, HOME, ENTER, TAB, DELETE, etc.
directionstring
Swipe direction
durationnumber
Duration in ms (long_press default: 1000, swipe default: 300)
intervalnumber
Delay between taps in ms for double_tap (default: 100)
targetPidnumber
Desktop only: PID of target process
hintsboolean
Return hints about what changed after the action (default: true, set false to disable)
platformstring
Target platform. If not specified, uses the active target.
deviceIdstring
Target device ID for multi-device. If omitted, uses active device.
示例调用
{
  "tool": "input",
  "arguments": {
    "action": "tap"
  }
}
ui

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.

Input(真实 schema)
actionstringrequired
textstring
Element text to search/check (partial match, case-insensitive)
labelstring
iOS: Find by accessibility label
resourceIdstring
Android: Find by resource ID (partial match)
classNamestring
Find by class name
clickableboolean
Android: Filter by clickable state
visibleboolean
iOS: Filter by visibility
showAllboolean
Show all elements including non-interactive (tree only)
compactboolean
Compact output: only interactive elements, short format (tree only)
formatstring
Output format. semantic = grouped by role, minimal tokens
descriptionstring
Natural language description of element to tap (find_tap only)
minConfidencenumber
Minimum confidence score 0-100 for find_tap (default: 30)
pidnumber
Process ID of target application (tap_text only)
exactMatchboolean
Require exact text match for tap_text (default: false)
freshboolean
Force bypass cache and fetch live UI tree
timeoutnumber
Max wait time in ms for wait (default: 5000)
intervalnumber
Poll interval in ms for wait (default: 500)
platformstring
Target platform. If not specified, uses the active target.
deviceIdstring
Target device ID for multi-device. If omitted, uses active device.
walkToClickableboolean
If matched element is non-clickable (e.g., a TextView label), walk up to the smallest containing clickable ancestor. Default true. Set false to tap the matched element directly even if non-clickable (rare).
示例调用
{
  "tool": "ui",
  "arguments": {
    "action": "tree"
  }
}
app

App lifecycle: launch, stop, install, list

Input(真实 schema)
actionstringrequired
packageNamestring
Alias for 'package'. App package name (Android) or bundle ID (iOS). Either 'package' or 'packageName' can be used.
packagestring
Package name (Android) or bundle ID (iOS), e.g., com.android.settings or com.apple.Preferences
platformstring
Target platform. If not specified, uses the active target.
deviceIdstring
Target device ID for multi-device. If omitted, uses active device.
pathstring
Path to APK (Android) or .app bundle (iOS)
delayMsnumber
Delay between stop and launch in ms (default: 500). Useful so OS releases resources.
示例调用
{
  "tool": "app",
  "arguments": {
    "action": "launch"
  }
}
system

System operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer.

Input(真实 schema)
actionstringrequired
commandstring
Shell command to execute (shell)
urlstring
URL to open (open_url)
msnumber
Duration in milliseconds (wait, default: 1000)
levelstring
Log level filter (logs)
tagstring
Filter by tag (logs, Android only)
linesnumber
Number of log lines (logs, default: 100)
packagestring
Package name (logs, permissions)
permissionstring
Permission to grant/revoke (permission_grant/revoke)
fieldTextstring
Find input field by text before paste (clipboard_paste)
fieldIdstring
Find input field by resource ID before paste (clipboard_paste)
localPathstring
Local file path (file_push/pull)
remotePathstring
Remote file path (file_push/pull)
platformstring
Target platform. If not specified, uses the active target.
示例调用
{
  "tool": "system",
  "arguments": {
    "action": "activity"
  }
}
flow

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).

Input(真实 schema)
actionstringrequired
commandsarray
Array of commands to execute sequentially
stopOnErrorboolean
Stop execution on first error (default: true)
turboboolean
[experimental] Rich UI feedback per step. Compact UI tree after each step, screenshot on failure.
stepsarray
Steps to execute sequentially
maxDurationnumber
Max total duration in ms (default: 30000, max: 60000)
platformstring
Target platform. If not specified, uses the active target.
argsobject
Arguments for the action (deviceId will be injected per device)
devicesarray
Array of device IDs to target. Use device(action:'list') to get available devices.
示例调用
{
  "tool": "flow",
  "arguments": {
    "action": "batch"
  }
}
repl_spawn

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.

Input(真实 schema)
idstringrequired
Session name (unique)
cmdstringrequired
Command line to spawn
cwdstring
envobject
colsinteger
rowsinteger
promptRegexstring
shellboolean
Run cmd via /bin/sh -c so shell syntax (env prefixes, 2>&1, pipes, globs, &&) works.
示例调用
{
  "tool": "repl_spawn",
  "arguments": {
    "id": "…",
    "cmd": "…"
  }
}
repl_send

Write text to a REPL session. Appends a newline by default.

Input(真实 schema)
idstringrequired
textstringrequired
newlineboolean
示例调用
{
  "tool": "repl_send",
  "arguments": {
    "id": "…",
    "text": "…"
  }
}
repl_key

Send a control key (enter/ctrl-c/ctrl-d/tab/arrows) to a session.

Input(真实 schema)
idstringrequired
keystringrequired
示例调用
{
  "tool": "repl_key",
  "arguments": {
    "id": "…",
    "key": "…"
  }
}
repl_expect

Block until a prompt regex matches, the session idles, the child exits, or the timeout fires.

Input(真实 schema)
idstringrequired
regexstring
idleMsinteger
timeoutMsinteger
示例调用
{
  "tool": "repl_expect",
  "arguments": {
    "id": "…"
  }
}
repl_snapshot

Read the current emulated terminal screen for a session. Output is redacted for common secret patterns unless disabled at plugin construction time.

Input(真实 schema)
idstringrequired
tailinteger
Trailing lines to return
示例调用
{
  "tool": "repl_snapshot",
  "arguments": {
    "id": "…"
  }
}
repl_list

List active REPL sessions and their statuses.

Input(真实 schema)
无参数
示例调用
{
  "tool": "repl_list",
  "arguments": {}
}
repl_kill

Terminate a REPL session (SIGTERM, then SIGKILL).

Input(真实 schema)
idstringrequired
示例调用
{
  "tool": "repl_kill",
  "arguments": {
    "id": "…"
  }
}

综合分

Canlah Score55
归属岗位Hephaestus · 页面优化工程师
岗位分值×1.10
★ Stars309
↓ 下载量5.9k
工具数(实测)14
npm 包claude-in-mobile
✓ 已连通:字段来自真实的 tools/list(工具清单)。工具本身尚未真实调用。

效果测评卡

进行中 · 待运行
任务成功率
输出质量 (LLM 评审)
延迟
成本 / token
稳定性

真实 I/O 已解决「输入输出是什么」;下一步接 agent 真跑,量化「效果好不好」。

取用 / 安装

npx -y claude-in-mobile
同岗位其他 skill
iPhone Control
blitzdotdev/iphone-mcp
✓ I/O · 10

Provides direct control over iOS simulators and physical iPhones through a unified interface that combines Facebook's idb for simulators and WebDriverAgent for physical devices. Features automated device discovery, real-time screen streaming via WebSocket for physical devices, and comprehensive interaction tools including tap, swipe, text input, button presses, screenshot capture, app launching, and UI element scanning. Supports both global and project-scoped setup with auto-configuration for Claude Code, Cursor, Codex, and OpenCode.

Hephaestus83216
38
WeChat Mini-Program Agent
chaixueyuan/weapp-agent-mcp
✓ I/O · 44

WeChat Mini-Program Agent enables AI-driven automation and testing of WeChat Mini Programs through a wrapper around miniprogram-automator's WebSocket interface to WeChat DevTools. Supported operations include page navigation, screenshot capture, UI element interaction, DOM inspection, and scenario testing. A serial execution model ensures predictable test flows for agent-first development workflows.

Hephaestus72.2k
35
BrowserGenie
browsergenie/mcp
✓ I/O · 112

MCP server for Chrome browser automation via a companion Chrome extension. Provides 50+ tools covering navigation, element clicking, text input, screenshot capture, touch gesture simulation, macro recording and replay, DevTools inspection, and accessibility auditing. Communicates with the extension via a local WebSocket bridge at localhost:7890. Written in TypeScript, Apache 2.0 licensed.

Hephaestus2476
26