Claude Mobile
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.
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。
deviceDevice management + module loading. list/set/set_target/get_target: devices. enable_module/disable_module/list_modules: load browser/desktop/store tools on demand.
actionstringrequireddeviceIdstringplatformstringtargetstringmoduleanycategorystring{
"tool": "device",
"arguments": {
"action": "list"
}
}screenScreen capture and annotation. capture: screenshot with compression/diff. annotate: screenshot with element bounding boxes.
actionstringrequiredplatformstringpresetstringcompressbooleanmaxWidthnumbermaxHeightnumberqualitynumbermonitorIndexnumberdiffbooleandiffThresholdnumberwaitForStablebooleandeviceIdstring{
"tool": "screen",
"arguments": {
"action": "capture"
}
}inputInput actions. tap/double_tap/long_press: coords or text/id/label/index. swipe: direction or coords. text: type text. key: press key.
actionstringrequiredxnumberynumberx1numbery1numberx2numbery2numbertextstringresourceIdstringlabelstringindexnumberkeystringdirectionstringdurationnumberintervalnumbertargetPidnumberhintsbooleanplatformstringdeviceIdstring{
"tool": "input",
"arguments": {
"action": "tap"
}
}uiUI 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.
actionstringrequiredtextstringlabelstringresourceIdstringclassNamestringclickablebooleanvisiblebooleanshowAllbooleancompactbooleanformatstringdescriptionstringminConfidencenumberpidnumberexactMatchbooleanfreshbooleantimeoutnumberintervalnumberplatformstringdeviceIdstringwalkToClickableboolean{
"tool": "ui",
"arguments": {
"action": "tree"
}
}appApp lifecycle: launch, stop, install, list
actionstringrequiredpackageNamestringpackagestringplatformstringdeviceIdstringpathstringdelayMsnumber{
"tool": "app",
"arguments": {
"action": "launch"
}
}systemSystem operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer.
actionstringrequiredcommandstringurlstringmsnumberlevelstringtagstringlinesnumberpackagestringpermissionstringfieldTextstringfieldIdstringlocalPathstringremotePathstringplatformstring{
"tool": "system",
"arguments": {
"action": "activity"
}
}flowFlow orchestration: batch (multi-command), run (multi-step automation with loops/conditionals), parallel (same action on multiple devices). Use turbo:true for rich feedback (experimental).
actionstringrequiredcommandsarraystopOnErrorbooleanturbobooleanstepsarraymaxDurationnumberplatformstringargsobjectdevicesarray{
"tool": "flow",
"arguments": {
"action": "batch"
}
}repl_spawnStart 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.
idstringrequiredcmdstringrequiredcwdstringenvobjectcolsintegerrowsintegerpromptRegexstringshellboolean{
"tool": "repl_spawn",
"arguments": {
"id": "…",
"cmd": "…"
}
}repl_sendWrite text to a REPL session. Appends a newline by default.
idstringrequiredtextstringrequirednewlineboolean{
"tool": "repl_send",
"arguments": {
"id": "…",
"text": "…"
}
}repl_keySend a control key (enter/ctrl-c/ctrl-d/tab/arrows) to a session.
idstringrequiredkeystringrequired{
"tool": "repl_key",
"arguments": {
"id": "…",
"key": "…"
}
}repl_expectBlock until a prompt regex matches, the session idles, the child exits, or the timeout fires.
idstringrequiredregexstringidleMsintegertimeoutMsinteger{
"tool": "repl_expect",
"arguments": {
"id": "…"
}
}repl_snapshotRead the current emulated terminal screen for a session. Output is redacted for common secret patterns unless disabled at plugin construction time.
idstringrequiredtailinteger{
"tool": "repl_snapshot",
"arguments": {
"id": "…"
}
}repl_listList active REPL sessions and their statuses.
{
"tool": "repl_list",
"arguments": {}
}repl_killTerminate a REPL session (SIGTERM, then SIGKILL).
idstringrequired{
"tool": "repl_kill",
"arguments": {
"id": "…"
}
}综合分
效果测评卡
进行中 · 待运行真实 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」。
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.
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.
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.