Tauri MCP Server
An MCP server that enables AI assistants to build, test, and debug Tauri v2 applications through UI automation (screenshots, clicks, typing, element finding), IPC monitoring, log streaming, and mobile device management.
README
<div align="center">
<img src="docs/public/logo.svg" alt="MCP Server Tauri" width="120" height="120" />
MCP Server Tauri
Give your AI assistant superpowers for Tauri development
Documentation · Getting Started · Available Tools
</div>
A Model Context Protocol (MCP) server that enables AI assistants like Claude, Cursor, and Windsurf to build, test, and debug Tauri® v2 applications. Screenshots, DOM state, and console logs from your running app give the AI rich context to understand what's happening—and tools to interact with it.
✨ Features
| Category | Capabilities |
|---|---|
| 🎯 UI Automation | Screenshots, clicks, typing, scrolling, element finding, visual element picker |
| 🔍 IPC Monitoring | Capture and inspect Tauri IPC calls in real-time |
| 📱 Mobile Dev | List iOS simulators & Android emulators |
| 📋 Logs | Stream console, Android logcat, iOS, and system logs |
Disclaimer: This MCP was developed using agentic coding tools. It may contain bugs.
Independent downstream fork: This distribution is maintained by Hushlor and is released independently of the original hypothesi/mcp-server-tauri project. It preserves the upstream MIT license and attribution while allowing downstream features and releases without upstream approval.
🚀 Quick Start
Prerequisites
- Node.js 20+ and npm
- Rust and Cargo (for Tauri development)
- Tauri CLI:
npm install -g @tauri-apps/cli@next - For mobile: Xcode (macOS) or Android SDK
1. Configure Your AI Assistant
Use aix to add the server to your AI assistant:
npx -y @a1st/aix add mcp tauri --command 'npx @hushlor/tauri-mcp-server' --user
Supported clients: claude-code, cursor, windsurf, vscode, cline, roo-cline, claude, zed, goose, warp, codex
[!TIP]
aixautomatically detects your installed AI assistants and configures them.
Restart your AI assistant after adding the configuration.
CLI Usage
If you want to call the tools directly from a terminal instead of from an MCP client:
npm install -g @hushlor/tauri-mcp-cli
tauri-mcp driver-session start --port 9223
tauri-mcp webview-screenshot --file screenshot.png
The CLI uses MCPorter keep-alive support so driver_session state survives across separate commands.
2. Set Up the MCP Bridge Plugin
Ask your AI assistant to help configure your Tauri app:
"Help me set up the Tauri MCP Bridge plugin"
Your AI will:
- Examine your project to see what's already configured
- Show you what changes are needed (Cargo.toml, plugin registration, etc.)
- Ask for your permission before making any modifications
That's it! The AI handles all the setup details while keeping you in control. 🎉
<details> <summary><strong>Manual Setup</strong></summary>
If you prefer to set up manually, see the Getting Started guide or the plugin documentation.
</details>
💬 Slash Commands (Prompts)
| Command | Description |
|---|---|
/setup |
Set up or update the MCP bridge plugin in your Tauri project |
/fix-webview-errors |
Find and fix JavaScript errors in your webview |
/select |
Visually select an element in your app — returns metadata and screenshot |
Just type the command in your AI assistant to start a guided workflow.
🧰 Available Tools (22 total)
<details> <summary><strong>Setup & Configuration</strong></summary>
| Tool | Description |
|---|---|
get_setup_instructions |
Get setup/update instructions for the MCP Bridge plugin |
</details>
<details> <summary><strong>UI Automation</strong> — Screenshots, clicks, typing, and more</summary>
| Tool | Description |
|---|---|
driver_session |
Start/stop/status automation session |
webview_find_element |
Find elements by selector |
read_logs |
Read console, Android, iOS, or system logs |
webview_interact |
Click, scroll, swipe, focus, long-press |
webview_screenshot |
Capture webview screenshots |
native_dialog_snapshot |
Inspect app-owned native Windows dialog chains and navigation controls |
native_dialog_interact |
Invoke, set single/multiple paths, or select native Windows dialog controls |
webview_keyboard |
Type text or send key events |
webview_wait_for |
Wait for elements, text, or events |
webview_get_styles |
Get computed CSS styles |
webview_execute_js |
Execute JavaScript in webview |
webview_dom_snapshot |
Get structured accessibility tree snapshot |
webview_select_element |
Visual element picker — user clicks an element, returns metadata + screenshot |
webview_get_pointed_element |
Get metadata for element user Alt+Shift+Clicked |
manage_window |
List windows, get info, or resize |
Multi-Window Support: All webview tools accept an optional
windowIdparameter to target specific windows. Usemanage_windowwithaction: "list"to discover available windows.
Native Windows dialogs:
native_dialog_*tools require an interactive desktop and expose only same-process dialogs whose owner chain leads to the targeted Tauri window. They support single/multi-file Open, Save, folder selection, nested confirmations, and advertised navigation controls, but not toast notifications or other applications.
</details>
<details> <summary><strong>IPC & Plugin</strong> — Deep Tauri integration</summary>
| Tool | Description |
|---|---|
ipc_execute_command |
Execute Tauri IPC commands |
ipc_get_backend_state |
Get app metadata and state |
ipc_monitor |
Start/stop IPC monitoring |
ipc_get_captured |
Get captured IPC traffic |
ipc_emit_event |
Emit custom events |
</details>
<details> <summary><strong>Mobile Development</strong> — Device listing</summary>
| Tool | Description |
|---|---|
list_devices |
List Android devices and iOS simulators |
</details>
🏗️ Architecture
┌─────────────────────────────────────────────────────────────────┐
│ AI Assistant │
│ (Claude, Cursor, Windsurf) │
└─────────────────────────┬───────────────────────────────────────┘
│ MCP Protocol (stdio)
▼
┌─────────────────────────────────────────────────────────────────┐
│ MCP Server (Node.js) │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────────────┐ │
│ │ Manager │ │ Driver │ │ Monitor │ │
│ │ CLI/Config │ │ UI Automation│ │ Logs/IPC Events │ │
│ └──────────────┘ └──────┬───────┘ └──────────────────────┘ │
└─────────────────────────────┼───────────────────────────────────┘
│ WebSocket (port 9223)
▼
┌─────────────────────────────────────────────────────────────────┐
│ Tauri Application │
│ ┌──────────────────────────────────────────────────────────┐ │
│ │ MCP Bridge Plugin (Rust) │ │
│ │ IPC Commands • Events • Backend State │ │
│ └──────────────────────────────────────────────────────────┘ │
│ ┌──────────────────────────────────────────────────────────┐ │
│ │ Webview (DOM/UI) │ │
│ └──────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
Why this approach?
- ✅ Rich AI context — Screenshots, DOM, and logs help the AI understand your app's state
- ✅ Cross-platform — Works on Linux, Windows, macOS, Android, and iOS
- ✅ No external drivers — No Selenium, Playwright, or browser automation needed
- ✅ Native integration — Direct access to Tauri's IPC and backend
🧑💻 Development
# Clone and install
git clone https://github.com/Hushlor/mcp-server-tauri.git
cd mcp-server-tauri
npm install
# Build all packages
npm run build
# Run tests
npm test
# Development mode
npm run dev -w @hushlor/tauri-mcp-server
<details> <summary><strong>Project Structure</strong></summary>
mcp-server-tauri/
├── packages/
│ ├── mcp-server/ # MCP server (TypeScript)
│ ├── cli/ # Published CLI wrapper
│ ├── tauri-plugin-mcp-bridge/ # Tauri plugin (Rust + JS bindings)
│ └── test-app/ # Test Tauri application
├── docs/ # VitePress documentation
└── specs/ # Architecture specs
</details>
<details> <summary><strong>Releasing</strong></summary>
# Validate the current coordinated release locally (no publish/tag)
node scripts/release-package.js 0.14.0 --dry-run
Publishing packages or creating and pushing tags requires explicit authorization. See specs/releasing.md for the bootstrap and coordinated release procedure.
</details>
📚 Documentation
- Full Documentation — Guides, API reference, and examples
- MCP Server Package — Server implementation details
- MCP Bridge Plugin — Tauri plugin documentation
🤝 Contributing
Contributions are welcome! Please:
- Follow existing code patterns
- Add tests for new features
- Update documentation
- Ensure
npm testandnpm run standardspass
Other Notes
This project is tested with BrowserStack.
📄 License
MIT © Hushlor. Original upstream copyright and attribution are preserved in LICENSE; see hypothesi/mcp-server-tauri for provenance.
Trademark Notice
TAURI® is a registered trademark of The Tauri Programme within the Commons Conservancy. https://tauri.app/
This project is not affiliated with, endorsed by, or sponsored by The Tauri Programme within the Commons Conservancy.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。