iphone-use
Related Servers
Alternatives to iphone-use
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control real iPhones and simulators on macOS, allowing for UI interaction, testing, and automation.58 npm92MIT
- AlicenseAqualityAmaintenanceEnables AI agents to drive an iPhone or iOS Simulator through 30 tools and 4 resources, using an observe/act/verify loop with built-in safety approvals.3141 PyPI3MIT
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables 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.43 npm10MIT

Phone Harness MCPofficial
AlicenseAqualityBmaintenanceLets AI agents drive real iPhones and Androids hosted in the cloud over HTTPS — taking screenshots, inspecting on-screen elements, tapping, typing, swiping, and launching apps — with no pairing, adb, or Mac required. It can run locally over stdio or as a hosted streamable HTTP endpoint supporting API keys and OAuth sign-in.15MIT- AlicenseBqualityAmaintenanceEnables 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
- AlicenseNot gradedqualityAmaintenanceFree, open-source Mac app and MCP server that lets AI agents take screenshots, tap, swipe, type and launch apps on a real iPhone. Includes owner-approved clients, an activity log and pause controls; supports USB and Wi-Fi after pairing.12Apache 2.0
- AlicenseNot gradedqualityAmaintenanceLets AI agents see and use a real Android phone over Wi-Fi: read the screen, find elements by text or ID, tap, type, swipe, take screenshots and read notifications, without ADB or root.458MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to control iOS Simulator apps by reading the screen as compact text instead of screenshots and returning the updated screen after every action. Supports tapping, typing, scrolling, key presses, and app or URL launches with one tool call per step instead of two.11MIT
TDQS
Scored across 41 tools
Most tools target clearly distinct capabilities, and the detailed descriptions explicitly differentiate close variants such as phone_tap, phone_tap_element, and phone_tap_label, or phone_screen, phone_screenshot, and phone_screen_frame. A few overlapping clusters remain—tap/scroll/observation/flow families—but their boundaries are largely well documented.
All tools use the predictable phone_ prefix and snake_case, making the set easy to scan. The pattern is mostly consistent, though it mixes verb-first names (phone_tap, phone_install_app) with noun-style read tools (phone_status, phone_elements) and one branded outlier (phone_jev_run).
With 41 tools, the surface is heavy for an agent to navigate, especially because several are niche administrative or internal tools. While the broad iPhone-automation domain justifies many capabilities, this count is well above a well-scoped set and increases selection cost.
The set covers a remarkably full lifecycle: app discovery, UI inspection, tapping, typing, scrolling, flows, installation, login, recording, diagnostics, location simulation, home layout, ownership, and metrics. Minor gaps exist—for example, no standalone direct launch/uninstall or clipboard/notification operations—but they are largely workable through phone_run_steps and related tools.