What are the system requirements?
Java 17 or higher, macOS with Xcode installed, Node.js, and Appium. For physical iOS devices, Carthage and developer-mode configuration are also required.
@sycophant21
Basic information
This project is a Java-based UI automation framework that integrates with Appium and utilizes LLMs (like Claude) to drive intelligent test actions on mobile devices and simulators.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"promptium": {
"command": "sh",
"args": [
"-c",
"curl -sL https://github.com/sycophant21/promptium/releases/latest/download/Promptium_v0.0.1.jar -o /tmp/promptium-mcp-server.jar && java -jar /tmp/promptium-mcp-server.jar"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Promptium is a Java-based UI automation framework that integrates with Appium and uses large language models (like Claude) to drive intelligent test actions on mobile devices and simulators. It implements a Model Context Protocol (MCP) server for context-aware, language-driven test flows.
Install Appium (via npm) and Xcode on macOS, then configure Claude Desktop’s MCP settings by adding the Promptium JAR to claude_desktop_config.json. The JAR can be downloaded from GitHub releases or compiled locally with Maven (mvn package).
Java 17 or higher, macOS with Xcode installed, Node.js, and Appium. For physical iOS devices, Carthage and developer-mode configuration are also required.
In Claude Desktop, go to Settings > Developer > Edit Config, then add a `promptium` entry to `mcpServers` in `claude_desktop_config.json` with the command to run the JAR (either from a downloaded release or a local build).
No. The README only describes iOS device/simulator setup using Appium’s XCUITest driver.
A physical device is only needed for testing on real iOS hardware; testing can also be done using an iOS simulator.
The server starts automatically when Claude Desktop invokes the configured command (`java -jar ...`). It can also be run manually via the command line by executing the compiled JAR.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Comments