somew1nd
9a5aaf99b7
- Showcase UI Reorganization: * Move web UI dashboard from root directory into apps/showcase_ui/ for cleaner project structure * Add 'artemis ui' CLI command (artemis/interfaces/cli/commands/ui.py) and launcher scripts for the interactive showcase console - Standalone MCP Server & Notifiers (mcp_server/): * Implement dedicated MCP server package with mobile automation tools (device_state, inspect_trace, task_manager, task_runner) * Add multi-channel notifiers (AgentAPI, Desktop notifications, Webhooks, File output, and Composite routing) * Introduce background task runner and trace store for autonomous mobile execution monitoring - Cross-Platform Runtime & Toolchain Support: * Add artemis/platform/ with OS-specific implementations for Linux, macOS (Darwin), and Windows * Add artemis/runtime/supervisor.py for resilient process and agent runtime supervision * Add artemis/toolchain/ with dependency resolution and SDK descriptors * Add cross-platform launcher scripts (start.sh, start.bat) and installer scripts (scripts/install_deps.*) - Core Enhancements & Diagnostics: * Enhance coordinate normalization, OCR API fallback, and perception pipeline * Add credential validation (credentials_validator.py) and system diagnostics * Update bilingual documentation (README.md, README_CN.md) and architecture diagrams - Test Suite Expansion: * Add integration tests for cloud gateway, remote ADB, and Artemis login * Add unit tests covering core diagnostics, platform detection, toolchain, credentials validator, optional OCR, and MCP tools
69 lines
4.3 KiB
Markdown
69 lines
4.3 KiB
Markdown
# π Universal MCP Server for ARTEMIS
|
|
|
|
This directory contains the universal **Model Context Protocol (MCP)** server for **ARTEMIS**, enabling seamless mobile device automation inside AI IDEs and agents like **Cursor**, **Claude Code**, **OpenClaw**, **Windsurf**, and **Jetski**.
|
|
|
|
## ποΈ Architecture
|
|
|
|
```
|
|
mcp_server/
|
|
βββ __init__.py # Package exports (mcp, main)
|
|
βββ base.py # Shared FastMCP instance
|
|
βββ server.py # Server entrypoint (stdio / sse)
|
|
βββ rules.md # AI Agent Testing Mindset & system prompt rules for IDEs
|
|
βββ background/ # Background process execution
|
|
β βββ task_runner.py # Subprocess runner for Artemis Agent
|
|
βββ notifiers/ # Multi-environment notification adapters
|
|
β βββ base.py # BaseNotifier abstract class
|
|
β βββ agentapi.py # Jetski / Antigravity AgentAPI notifier
|
|
β βββ webhook.py # OpenClaw / CI / Discord / Slack webhook notifier
|
|
β βββ desktop.py # Native OS toast notifier
|
|
β βββ file.py # File audit logger
|
|
β βββ composite.py # Multi-channel notification dispatcher
|
|
βββ tools/ # Modular standard MCP tools
|
|
β βββ task_runner.py # mobile_run_task
|
|
β βββ task_manager.py # mobile_manage_task
|
|
β βββ device_state.py # mobile_get_device_state
|
|
β βββ inspect_trace.py # mobile_inspect_trace
|
|
βββ utils/ # Environment, device, and trace utilities
|
|
βββ device_utils.py # Cross-platform ADB and emulator resolver
|
|
βββ env_utils.py # Python interpreter and process manager
|
|
βββ trace_store.py # Traces directory and status manager
|
|
```
|
|
|
|
## π§ AI Agent Behavioral Rules (`rules.md`)
|
|
|
|
When connecting ARTEMIS to AI coding assistants like **Claude Code**, **Cursor**, or **Windsurf**, providing the assistant with domain-specific testing discipline is critical for generating reliable test code.
|
|
|
|
The included [`rules.md`](./rules.md) file contains the **Mobile Testing Mindset (ARTEMIS Integration)** guideline. It teaches the AI agent how to properly collaborate with ARTEMIS:
|
|
|
|
1. **The Runnable Code Principle & Active Exploration**: Instructs the AI to never guess or hallucinate UI transitions. Instead, it must first explore the live app via ARTEMIS MCP tools (`mobile_run_task`, etc.) to discover and verify real-world interaction paths before writing test scripts.
|
|
2. **Flash vs. Pro Routing Strategy**: Guides the AI to choose **Flash** for rapid, straightforward UI actions (< 30 steps) and **Pro** for complex multi-agent planning, polling loops, or video/log diagnosis.
|
|
3. **Latency & Timing Compensation**: Clarifies the difference between AI exploratory latency (e.g., model decision intervals) and the deterministic timing requirements of final test code.
|
|
4. **"Dynamic-First, Coordinate-Fallback" Locator Pattern**: Teaches the AI to prioritize dynamic UI locators (Resource IDs, OCR text, semantics) for layout resilience, while implementing absolute coordinate fallbacks for maximum execution reliability.
|
|
|
|
### How to Apply `rules.md` in Your IDE
|
|
* **Claude Code**: Copy or include the contents of `rules.md` in your project's `CLAUDE.md` file (or reference it directly in your instructions).
|
|
* **Cursor**: Copy the contents of `rules.md` into your `.cursorrules` or create a new rule file in `.cursor/rules/artemis.mdc`.
|
|
* **Windsurf / OpenClaw**: Add the rules to your global/workspace rules or agent system prompts so the assistant always follows verified mobile testing principles.
|
|
|
|
## π οΈ MCP Tools Overview
|
|
|
|
* **`mobile_run_task`**: Asynchronously launches an autonomous mobile automation task (`Flash` or `Pro` model).
|
|
* **`mobile_manage_task`**: Manages task lifecycle (`status`, `stop`, `inject_instruction`).
|
|
* **`mobile_get_device_state`**: Real-time observer (`screenshot` or OCR+XML `hierarchy`).
|
|
* **`mobile_inspect_trace`**: Granular trace inspection, visual action overlays, and agent reasoning.
|
|
|
|
## π How to Run & Configure
|
|
|
|
### CLI Execution
|
|
```bash
|
|
# Start server over stdio
|
|
python -m mcp_server
|
|
|
|
# Or via Artemis CLI
|
|
artemis mcp
|
|
```
|
|
|
|
### IDE Configuration
|
|
Run `artemis mcp --generate-config all` to generate ready-to-use configuration JSON for Cursor, Claude Code, OpenClaw, and Windsurf.
|