
Mirroir Mcp
io.github.jfarcandPublished by GitHub account jfarcandv0.45.0Updated Nov 6, 2026
Drive a stock iPhone via iPhone Mirroring: no Developer Mode, Xcode or WDA. LLM-free skill replay.
Overview
Drives a stock iPhone through macOS iPhone Mirroring, letting an agent read the screen, tap, type and swipe, then replay recorded runs without an LLM.
- What you can do
- Read the mirrored iPhone screen and inspect what apps show
- Tap, type, swipe and drag on the phone through the mirror
- Record a run and generate reusable skill files from it
- Replay compiled skills from the CLI with no AI in the loop
- Run one scenario across the phone, a browser and HTTP endpoints, with a drift verdict
- Play turn-based or tap-driven games frame by frame under a budget
- When to use it
- Useful when an agent should operate real App Store apps on a physical iPhone without Developer Mode, Xcode or jailbreak, or when a first exploratory run should become a deterministic, token-free replay for CI.
- Requirements
- macOS 15 or later with an iPhone connected through iPhone Mirroring; installed via npx or Homebrew; macOS Screen Recording and Accessibility permissions; a compatible MCP client. No Developer Mode, Xcode, jailbreak or on-device agent is needed.
Installation
In SourceWeft
- Open Mirroir Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
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, …):
Or install it yourself:
OpenClaw, Claude Desktop, Cursor, VS Code and the other clients: Install.
Then ask for something:
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_skillexplores 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-runis 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-runhas 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.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
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.
blockedAppskeeps 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: falseturns 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
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.
Source: README.md at commit 81c01b6
Tools
0Version history
8- v0.45.0LatestNov 6, 2026
- v0.44.0Nov 5, 2026
- v0.43.0Nov 4, 2026
- v0.42.0Oct 30, 2026
- v0.41.0Oct 29, 2026
- v0.40.1Oct 5, 2026
- v0.40.0Oct 4, 2026
- v0.39.0Sep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts