Mirroir Mcp

io.github.jfarcand由 GitHub 账号 jfarcand 发布v0.45.0更新于 Nov 6, 2026

Drive a stock iPhone via iPhone Mirroring: no Developer Mode, Xcode or WDA. LLM-free skill replay.

已验证STDIO仅桌面浏览器自动化开发者工具

概览

AI 生成的概览

通过 macOS 的 iPhone 镜像操控未越狱的 iPhone,让助手读取屏幕、点击、输入和滑动,并能不依赖大模型回放已录制的流程。

可以做什么
  • 读取镜像中的 iPhone 屏幕并查看各应用显示的内容
  • 通过镜像在手机上点击、输入、滑动和拖拽
  • 录制操作过程并据此生成可复用的技能文件
  • 在命令行中回放编译好的技能,全程不调用 AI
  • 用同一份场景同时驱动手机、浏览器和 HTTP 接口,并给出漂移判定
  • 按帧在预算内玩回合制或点击类游戏
适用场景
适合需要让助手操作真实 iPhone 上的 App Store 应用、又不想开启开发者模式、安装 Xcode 或越狱的场景;也适合把首次探索性操作变成可在 CI 中确定性、零 token 回放的测试。
运行要求
macOS 15 或更高版本,并通过 iPhone 镜像连接 iPhone;可用 npx 或 Homebrew 安装;需授予 macOS 屏幕录制与辅助功能权限;需要兼容的 MCP 客户端。无需开发者模式、Xcode、越狱或手机端代理。
安装前请注意
这等于把手机交给 AI 操作:一旦放开工具权限,就可能点击、输入、发送、购买、删除或更改设置。默认只暴露 12 个只读工具,其余需在 permissions.json 中允许;可用 blockedApps 阻止助手进入钱包、银行等敏感应用。它不会按下密码或 Touch ID 弹窗,但助手读到的屏幕内容会发送给客户端所用的大模型。除非关闭 updateCheck,否则每天会向 npm 做一次版本检查。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mirroir Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[mirroir-mcp]

mirroir-mcp

[npm version] [Build] [License] [macOS 15+] [Discord]

Let your agent use your real iPhone, then replay what it did without an LLM.

[An agent reads the commute time in Waze on a real iPhone, then posts it in a Slack channel]

A real run on a real iPhone, sped up: the agent reads the ETA in Waze, then posts it in Slack.

No Developer Mode, no Xcode, no WebDriverAgent, no jailbreak. mirroir-mcp works through macOS iPhone Mirroring, so it reaches any app on your phone, including App Store apps you could never build. It works from any MCP client, with 39 tools.

Quick start

You need macOS 15 or later and an iPhone connected through iPhone Mirroring. Paste this into your coding agent (Claude Code, Codex, Cursor, OpenClaw, …):

text
Set up mirroir-mcp so you can drive my iPhone: follow https://github.com/jfarcand/mirroir-mcp/blob/main/docs/onboarding.md step by step, and finish by reading back what my iPhone screen shows.

Or install it yourself:

bash
npx -y mirroir-mcp install    # or: brew tap jfarcand/tap && brew install mirroir-mcpnpx -y mirroir-mcp doctor     # names anything left to fix

OpenClaw, Claude Desktop, Cursor, VS Code and the other clients: Install.

Then ask for something:

Open Calendar, create a new event called "Dentist" next Tuesday at 2pm.
Open my Expo Go app, tap "LoginDemo", test the login screen with[email protected] / password123. Screenshot after each step.
Start recording, open Instagram, scroll the feed and open my profile, stop recording.

Why mirroir

  • Nothing to install on the phone. The iPhone stays stock: no signing, no provisioning profile, no on-device agent. If iPhone Mirroring shows it, mirroir can drive it.

  • Your Mac stays yours. Taps, typing and swipes reach the mirror without bringing it to the front, so you can keep working. Drags and two-finger gestures bring it forward for a moment, then hand your app back.

  • Explore once, replay without an LLM. generate_skill explores an app and writes SKILL.md files. A compiled skill replays from the CLI with no AI in the loop (mirroir test), so CI runs are deterministic and cost no tokens.

  • One test across phone, web and backend. mirroir-run is our companion test runner, a separate binary. One YAML scenario can drive the iPhone, a browser, HTTP endpoints and subprocesses, then compare what the page and the phone showed. See Web and iOS in one scenario.

  • Drift fails loudly. mirroir-run has a third verdict beside pass and fail: DRIFT, exit code 65, when every assertion held but the output moved past its baseline. Your CI lane decides whether drift blocks a merge.

  • It plays games, too. A scene: step plays a turn-based or tap-driven game, frame by frame, under a hard budget. See Games.

    [The console and a real iPhone side by side during a full chess game: each move is logged as it is played, ending in checkmate against the Maximum bot on Chess.com]

    A real game on a real iPhone: the model reads the board, Stockfish picks the moves, mirroir plays them against Chess.com's strongest bot. The opening runs at 2.5×, the middle game at 45×, the finish at 2×.

How it compares

mirroirphone-harnessmobile-mcpAppium
Physical iPhone, no Developer Mode or signingYes — stock phone via iPhone MirroringYes — stock phone via iPhone MirroringUSB-connected, trusted device (see its README)No — WebDriverAgent via Xcode, Developer Mode
App Store apps you can't buildYesYesYesYes, on a provisioned device
Your own iPhone from any MCP clientYesNo — its MCP server is cloud-only; local phones use its CLIYesThrough the separate appium-mcp
Replay without an LLMYes — compiled skills, mirroir testPython scripts you write; no recorder or compiled replayNo — the agent drives every runYes — test code
Distinct drift verdictYes — DRIFT, exit 65NoNoNo — pass / fail
One scenario across iPhone + web + HTTPYes — mirroir-runNoNoVia your own test code
AndroidNo — an emulator window can be driven only as a generic macOS windowYesYesYes
iOS SimulatorNoNoYesYes
Hosted cloud phonesNoYes — Phone Harness CloudYes — Mobile Next CloudVia third-party device clouds

phone-harness is the closest tool here: it also drives a stock iPhone through iPhone Mirroring, and it adds Android and hosted phones, which mirroir doesn't have. mobile-mcp and Appium cover Android and simulators too. mirroir goes further after the agent's first run: that run becomes a replay that needs no LLM, and a test that tells you when the output moves.

Safety

Giving an AI access to your phone demands defense in depth, so mirroir-mcp is fail-closed.

  • Read-only until you say otherwise. Without a config file, only the 12 read-only tools are exposed. Every tool that changes something stays hidden from the client until you allow it in permissions.json.
  • Sensitive apps can be blocked. blockedApps keeps the AI out of apps like Wallet or Banking, even when other tools are allowed.
  • Passwords stay yours. mirroir never presses a sheet that asks for a password or Touch ID, and it tells agents to ask you before sending, buying, deleting or changing a setting.
  • No root, no daemon, no telemetry. It runs as your user with Screen Recording and Accessibility. The one network call it makes by default is a once-a-day version check against npm (updateCheck: false turns it off). What your agent reads from the screen goes to whichever model your client uses.
  • Kill switch. Close iPhone Mirroring to stop all input instantly.

See Security for the full threat model.

Documentation

InstallEvery install path, per-client setup, updating, uninstalling
OnboardingSetup written for the agent: prerequisites, install, doctor, and a read-only proof
Tools ReferenceAll 39 tools, parameters, and input workflows
How mirroir sees the screenThe observe, reason, act loop; OCR, icon detection, AI vision
Skills, exploration and CIAPP.md, skills, generate_skill, mirroir test, compiled replay, AI diagnosis, patterns
mirroir-runReplay across iPhone, web, HTTP and subprocesses; GitHub Actions; Maestro import
GamesShell and scene, the scene: step, game controls
CLI ToolsRecorder, doctor, keyboard layout
ConfigurationAll settings: screen intelligence, input timing, exploration, AI providers
FAQSecurity, focus stealing, keyboard layouts, embacle/vision mode
SecurityThreat model, kill switch, and recommendations
PermissionsFail-closed permission model and config file
Known LimitationsFocus stealing, keyboard layout gaps, autocorrect
Patterns & SkillsElement patterns, screen recipes, APP.md app descriptions, and the detection pipeline
Exploring a New AppStep-by-step playbook for onboarding a new app — APP.md, permissions, components, exploration goal
YOLO Icon DetectionRecommended YOLO models, CoreML setup, and configuration
Compiled SkillsZero-OCR skill replay
TestingFakeMirroring, integration tests, and CI strategy
Web and iOS in one scenarioHow mirroir-run hands iOS blocks to mirroir-mcp, and how cross_surface compares a browser with a phone
Cross-surface replaymirroir-run scenario grammar, .mirroir/ plan, SAMPLE.md, judge profiles, CI
TroubleshootingDebug mode and common issues
ContributingHow to add tools, commands, and tests
Skills MarketplaceSkill format, plugin discovery, and authoring

Community

Join the Discord server to ask questions, share skills, and discuss ideas. Contributions are welcome: see CONTRIBUTING.md. By submitting a patch, you agree to the Contributor License Agreement; your Git commit metadata serves as your electronic signature.


Why "mirroir"? — It's the old French spelling of miroir (mirror). A nod to the author's roots, not a typo.

来源:README.md,提交 81c01b6

工具

0
SourceWeft 曾在隔离沙箱中以无凭据方式启动该软件包一次,以列出其工具,但未能完成:软件包安装失败。

版本历史

8
  1. v0.45.0最新Nov 6, 2026
  2. v0.44.0Nov 5, 2026
  3. v0.43.0Nov 4, 2026
  4. v0.42.0Oct 30, 2026
  5. v0.41.0Oct 29, 2026
  6. v0.40.1Oct 5, 2026
  7. v0.40.0Oct 4, 2026
  8. v0.39.0Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分