Control a real iPhone remotely through macOS iPhone Mirroring via screenshot, tap, swipe, and type commands. Built for developers automating iOS testing, demos, and interaction workflows.
io.github.jfarcand/iphone-mirroir-mcp
Local install
STDIO
No auth required
How models use it and what it is built for.
Control a real iPhone remotely through macOS iPhone Mirroring via screenshot, tap, swipe, and type commands. Built for developers automating iOS testing, demos, and interaction workflows.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Jfarcand Iphone Mirroir.
Paste any of these into Agent Studio after connecting Jfarcand Iphone Mirroir.
Common questions about connecting and running Jfarcand Iphone Mirroir.
What do I need to use this MCP server?
You need a Mac running macOS with iPhone Mirroring enabled and an iPhone connected. The server communicates with the mirrored iPhone session to send tap, swipe, type, and screenshot commands.
Can I use this for automated iOS app testing?
Yes. You can take screenshots to verify UI state, tap buttons, swipe through screens, and type input—making it suitable for scripted testing workflows and demo automation.
Does this work with any iPhone or only specific models?
It works with any iPhone that supports macOS iPhone Mirroring (iOS 17.1+). The server controls whatever iPhone is currently mirrored on your Mac.
How do I install and start using it?
Run `npx iphone-mirroir-mcp@0.4.1` to install and launch the server. It communicates via stdio, so connect it to your MCP client and start sending commands.
What's the difference between this and Xcode's UI testing tools?
This server controls a real, mirrored iPhone through natural interaction commands (tap, swipe, type) rather than XCTest code. It's lighter-weight for demos and quick automation but lacks the deep app introspection of Xcode testing.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams