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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.