About XCRS Mobile & TV Automation
XCRS is an MCP server for automating tests on Apple simulators and physical devices, Android phones, and Android TV. It combines platform tooling in a target-aware workflow for mobile and TV app testing.
Key features
- 01Automate Apple simulators and devices
- 02Automate Android phones and TVs
- 03Target-aware automation workflow
- 04Optional Android accessibility and semantic taps
Use cases
- 01Test mobile apps on Apple and Android devices
- 02Automate app checks on Apple TV and Android TV
MCP support
Run with `xcrs --mcp` to expose cross-platform mobile and TV automation tools to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEXCRS Mobile & TV Automation
Cross-platform MCP tools for testing mobile and TV apps on Apple simulators, physical Apple devices, Android phones, and Android TV devices. XCRS combines Xcode, ControlKit, CoreDevice, and adb behind one target-aware automation workflow.
MCP Registry name: mcp-name: io.github.smbcloudXYZ/xcrs
Run the MCP server
cargo install xcrs
xcrs --mcp
Android tools use adb from ANDROID_SDK_ROOT, ANDROID_HOME, the standard
Android SDK locations, or PATH. Connect a device with USB debugging enabled
and authorize the host before selecting it with device_select.
For Android accessibility-tree inspection and semantic ui_tap, install the
optional XCRS AndroidKit companion runner. Raw adb
actions remain available without it.
The same automation profile is available from the full smbCloud CLI:
smb --mcp --scope automation
Repository
Source and documentation are available in the smbcloud-cli repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.