iphone-mcp
Related Servers
Alternatives to iphone-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to see and control a real iPhone over a USB cable on macOS. Provides screenshots, on-screen text reading, taps, swipes, typing, hardware buttons, app launching, and clipboard access without jailbreaking or installing anything on the phone.7MIT
- AlicenseAqualityBmaintenanceLet AI agents operate a real USB-connected iPhone from Linux — no Mac, no jailbreak, no paid developer account. Screenshots, taps, swipes, text input, element tree and app control via WebDriverAgent, with CoreDevice HID fallback.1742MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to operate a real iPhone from a Mac by reading the screen over USB and sending taps, swipes, typing, and app launches over Bluetooth, with every action returning a fresh screenshot so the agent can verify its work. Runs as a local MCP server, so agents can test iOS apps on physical devices and automate everyday phone tasks.40 npm10MIT
- AlicenseBqualityFmaintenanceEnables AI agents to see and operate a real USB-connected iPhone from a Linux Docker host — taking screenshots with region zoom, reading the element tree, tapping, swiping, long-pressing, typing text, pressing hardware buttons, listing/launching/terminating apps, and opening URLs. Automatically recovers from replugs and crashes, re-signs its automation agent before expiry, and falls back to a signing-free HID path on newer iOS.13MIT
- FlicenseAqualityAmaintenanceControl a real iPhone or iOS Simulator through a macOS daemon and XCTest runner over USB or Wi-Fi: read screen text, tap, type, swipe, inspect logs and replay flows with explicit outcomes. Browser sandbox: use readonly to inspect 12 preloaded flows without a phone. Reuse an existing sandbox from MCP Deployments, or delete it before starting another. Device control needs your Mac and iPhone.643505-
- AlicenseNot gradedqualityBmaintenanceThis MCP server gives AI agents eyes and hands on a real iPhone: they read the screen as a list of elements plus a screenshot, then tap, type, scroll, swipe, answer system permission prompts, press buttons, rotate, and open deep links to test any installed app. It runs over USB or Wi-Fi from Windows, Linux or macOS, with no Mac or Xcode needed, and can be limited to a named set of apps.5MIT
TDQS
Scored across 19 tools
The tools are cleanly separated by resource and action: session lifecycle, screen reading, gestures, text input, app control, and device locking. Overlaps such as tap vs tap_text, swipe vs scroll, and screenshot vs ui_tree are explicitly resolved in descriptions, so an agent can choose confidently.
All 19 tools use the iphone_ prefix and snake_case, yielding a predictable namespace. The only minor variation is that a few are noun-style read operations (iphone_status, iphone_screenshot, iphone_ui_tree) while most are verb-led, but the convention remains consistent and readable.
19 tools is slightly above the typical sweet spot but justified for a device-automation surface. Each tool covers a distinct capability, and no obvious redundant wrappers inflate the count.
Core lifecycle, observation, gesture, text-entry, app, and URL operations are covered, giving no major dead ends for UI automation. Minor gaps remain around clearing/replacing text, device settings, notifications, or advanced multi-touch, but these are outside the apparent scope.