The problem
Apple doesn't give the iPhone an API
You're building something that needs to touch iOS apps. Maybe an AI agent that books reservations. Maybe an automation that posts to Instagram. Maybe a test suite that needs real devices.
And you've discovered the truth: You don't have any good options.
Simulators don't run real apps
Third-party apps won't install and push notifications don't work. Services detect and block emulated environments instantly.
Hardware farms are expensive
Buying, racking, and maintaining real devices costs a fortune. Even more if you're paying someone else to do it.
Screen scraping breaks constantly
Every iOS update or app redesign breaks your scripts. You're stuck patching hacks instead of building your product.
The solution
TapKit is the iPhone API
Download TapKit on your Mac, plug in your iPhone, and your device instantly becomes a fully programmable API endpoint. No jailbreaking, no private APIs, no infrastructure to manage.
Download TapKit
Install the TapKit Mac app. No jailbreaking, no developer mode, no putting your phone in any weird state.
Connect your iPhone
Plug in your iPhone and follow the setup guide. Your phone stays in its normal state. Nothing is modified or compromised.
Your iPhone has an API
Screenshot, tap, swipe, type. Every action is now a REST call or MCP tool. Your agent can use any app on the phone.
Use cases
Anything you do on an iPhone,
your agent can do with TapKit
Social Media Automation
Automate posting, engagement, and content management across iOS-only and mobile-optimized social platforms at scale.
- Schedule and publish content
- Automate engagement workflows
- Manage multiple accounts
- Access iOS-exclusive features
AI Agent Testing
Build and evaluate mobile AI agents that can navigate apps, complete tasks, and interact with native iOS interfaces.
- End-to-end mobile agent evals
- Vision model benchmarking
- App interaction datasets
- Real-world testing environment
Mobile DevOps & QA
Automated testing, regression detection, and continuous integration for iOS apps on real hardware.
- CI/CD integration
- Visual regression testing
- Cross-device compatibility
- Automated smoke tests
Ways to use TapKit
Your workflow, your way
Whether you're a developer building agents or a team automating workflows, there's a TapKit interface that fits how you work.
Mac App
Native macOS app to control your iPhone directly from your desktop. Point-and-click automation builder, live device preview, and session management. No code required.
Web App
Access and control your devices from any browser. Build automations, watch live sessions, and manage your fleet from anywhere.
Claude Code
Connect TapKit as an MCP server in Claude Code and let your agent control an iPhone with native tool calls. Also works with Cursor, Windsurf, and any MCP-compatible client.
REST API
Full programmatic control over sessions, actions, and screenshots. Build your own agents, integrations, and automation pipelines from scratch.
Why TapKit
Real devices beat everything else
Emulators get blocked. Hardware doesn't scale. TapKit gives you the real thing. Managed, automated, and API-driven.
| Simulators | Hardware | TapKit ✦ | |
|---|---|---|---|
| Real iOS device | ✗ | ✓ | ✓ |
| App Store apps | ✗ | ✓ | ✓ |
| API-driven | ✓ | ✗ | ✓ |
| No hardware to manage | ✓ | ✗ | ✓ |
| Use it today | ✗ | ✗ | ✓ |
| Needs no iPhone app | ✓ | ✗ | ✓ |
| Built for agents | ✗ | ✗ | ✓ |
FAQ
Frequently asked questions
How does TapKit work?
TapKit gives you programmatic control of real, physical iPhones through Apple's Switch Control accessibility features. You send actions (tap, swipe, type) via our API, and they execute on actual hardware. No jailbreaks, no emulators, no detection.
Is this the same as an iOS simulator?
No. Simulators and emulators run virtual iOS environments that apps and services can detect and block. TapKit runs on real iPhones, so every interaction is identical to what a human user would produce. Your automations are undetectable.
What can I automate with TapKit?
Anything you can do on an iPhone. Social media management, app testing, form filling, content posting, data extraction, workflow automation. If it involves tapping a screen, TapKit can do it programmatically.
How do I connect my AI agent?
Use our MCP server to connect directly to Claude Code or Cursor, our REST API with a Python SDK for custom integrations, or our Mac and Web apps for no-code control. The typical agent loop is: screenshot → send to your vision model → get action → execute on device.
Do I need my own iPhone?
Yes, TapKit is bring-your-own-device. You connect your own iPhone to your Mac and TapKit turns it into an API. We're exploring hosted phone options for teams that don't want to manage their own hardware. Reach out if you're interested.
What does it cost?
TapKit starts at $100/month per phone with volume discounts for larger fleets. Get in touch for custom enterprise pricing.
Built for AI agents · integrates with
Simple pricing. No surprises.
- Use it with any agent
- Unlimited team members
- Remote phone control
- Start with one phone. Scale whenever.
- Priority support
Need more phones or a custom setup?
Let's talk →Get Started
Ship your mobile agent
today.
Join the companies building the next generation of mobile AI agents on TapKit's infrastructure.
Starting at $100/month per device · Volume discounts available