tauri-plugin-mcp
Enables AI assistants to automate and test Tauri desktop applications through the Model Context Protocol. It provides tools for app management, UI interaction, and state inspection across multiple platforms without requiring CDP dependencies.
README
tauri-plugin-mcp
Cross-platform Tauri test automation plugin via MCP (Model Context Protocol).
Enables AI assistants like Claude to interact with your Tauri desktop app for testing and automation.
Features
- Cross-platform: Windows (Named Pipes) + macOS/Linux (Unix Sockets)
- No CDP dependency: Works on all WebView backends including macOS WKWebView
- MCP integration: Direct integration with Claude Code and other MCP clients
Prerequisites
- Node.js >= 18
- Tauri v2.x
- pnpm (recommended) or npm
- Rust with cargo
Quick Start
- [ ] Add Rust plugin to
src-tauri/Cargo.toml - [ ] Install npm package:
pnpm add github:DaveDev42/tauri-plugin-mcp#main - [ ] Register plugin in
src-tauri/src/lib.rs - [ ] Add
mcp:defaultpermission - [ ] Initialize bridge in
main.tsx - [ ] Create
.mcp.jsonfor Claude Code
Installation
1. Rust Plugin (src-tauri/Cargo.toml)
[dependencies]
tauri-plugin-mcp = { git = "https://github.com/DaveDev42/tauri-plugin-mcp" }
2. Frontend API (package.json)
pnpm add github:DaveDev42/tauri-plugin-mcp#main
3. MCP Server
The MCP server is included in the package at:
node_modules/tauri-plugin-mcp/packages/tauri-mcp/dist/index.js
Setup
1. Register the plugin (src-tauri/src/lib.rs)
pub fn run() {
tauri::Builder::default()
.plugin(tauri_plugin_mcp::init())
.run(tauri::generate_context!())
.expect("error while running tauri application");
}
2. Add permissions
Option A: In tauri.conf.json or config/*.json5 (recommended)
{
"security": {
"capabilities": [{
"identifier": "main-capability",
"windows": ["main"],
"permissions": ["core:default", "mcp:default"]
}]
}
}
Option B: Separate file (src-tauri/capabilities/default.json)
{
"$schema": "../gen/schemas/desktop-schema.json",
"identifier": "default",
"windows": ["main"],
"permissions": ["core:default", "mcp:default"]
}
3. Initialize the bridge (main.tsx)
// Initialize MCP bridge for E2E testing (dev mode only)
if (import.meta.env.DEV) {
import('tauri-plugin-mcp').then(({ initMcpBridge }) => {
initMcpBridge().catch(err => {
console.warn('[MCP] Bridge initialization failed:', err);
});
});
}
MCP Server Configuration
Add to .mcp.json in your project root:
{
"mcpServers": {
"tauri-mcp": {
"command": "node",
"args": ["node_modules/tauri-plugin-mcp/packages/tauri-mcp/dist/index.js"],
"env": {
"TAURI_PROJECT_ROOT": "."
}
}
}
}
Available Tools
| Tool | Parameters | Description |
|---|---|---|
app_status |
- | Check if app is running |
launch_app |
wait_for_ready?: boolean, timeout_secs?: number, features?: string[] |
Launch Tauri app via pnpm tauri dev |
stop_app |
- | Stop the app |
snapshot |
- | Get accessibility tree (returns ref numbers) |
click |
ref?: number, selector?: string |
Click element by ref or CSS selector |
fill |
ref?: number, selector?: string, value: string |
Fill input field |
press_key |
key: string |
Press keyboard key |
navigate |
url: string |
Navigate to URL |
screenshot |
- | Take screenshot (uses html2canvas) |
evaluate_script |
script: string |
Execute custom JavaScript |
get_console_logs |
- | Get console logs |
get_network_logs |
- | Get network logs |
Using features parameter
To launch with Cargo features:
launch_app({ features: ["my_feature"] })
This runs: pnpm tauri dev --features my_feature
Usage Example
Typical testing workflow:
1. launch_app({ timeout_secs: 120 })
2. snapshot() # Get element refs
3. click({ ref: 5 }) # Click button by ref
4. fill({ selector: "input[name='email']", value: "test@example.com" })
5. screenshot() # Verify result
6. stop_app()
How It Works
Claude Code <-> MCP Server <-> Socket <-> Tauri Plugin <-> JS Bridge <-> Your App
- Rust Plugin creates IPC server (Unix socket or Windows named pipe)
- MCP Server connects to IPC and exposes tools to Claude
- JS Bridge (
initMcpBridge()) enables DOM operations in WebView
Socket Paths
- Unix:
{project_root}/.tauri-mcp.sock - Windows:
\\.\pipe\tauri-mcp-{hash}(hash derived from project path)
Troubleshooting
"MCP bridge not initialized"
The JS bridge isn't running. Check:
initMcpBridge()is called in your frontend code- App is running in dev mode (
import.meta.env.DEV) - Check browser console for initialization errors
Socket connection failed
- Ensure the app is running (
launch_appfirst) - On Windows, check pipe path in logs:
[tauri-plugin-mcp] full_path: \\.\pipe\tauri-mcp-XXXXX - On Unix, check if
.tauri-mcp.sockexists in project root
App launch timeout
- Increase
timeout_secs(default: 60) - Check if
pnpm tauri devworks manually - Look for build errors in terminal output
snapshot returns empty
- Wait for app to fully load (use
wait_for_ready: true) - Check if bridge initialized (look for
[MCP]logs in console)
License
MIT OR Apache-2.0
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。