Skip to main content
Glama

MCP Server Tauri

Give your AI assistant superpowers for Tauri development

npm version crates.io License: MIT Tauri v2

Documentation · Getting Started · Available Tools


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.

Related MCP server: tauri-plugin-mcp

🚀 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 @hypothesi/tauri-mcp-server' --user

Supported clients: claude-code, cursor, windsurf, vscode, cline, roo-cline, claude, zed, goose, warp, codex

TIP

aix automatically 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 @hypothesi/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:

  1. Examine your project to see what's already configured

  2. Show you what changes are needed (Cargo.toml, plugin registration, etc.)

  3. Ask for your permission before making any modifications

That's it! The AI handles all the setup details while keeping you in control. 🎉

If you prefer to set up manually, see the Getting Started guide or the plugin documentation.


💬 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 (21 total)

Tool

Description

get_setup_instructions

Get setup/update instructions for the MCP Bridge plugin

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

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 windowId parameter to target specific windows. Use manage_window with action: "list" to discover available windows.

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

Tool

Description

list_devices

List Android devices and iOS simulators


🏗️ 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/hypothesi/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 @hypothesi/tauri-mcp-server
mcp-server-tauri/
├── packages/
│   ├── mcp-server/              # MCP server (TypeScript)
│   ├── tauri-plugin-mcp-bridge/ # Tauri plugin (Rust + JS bindings)
│   └── test-app/                # Test Tauri application
├── docs/                        # VitePress documentation
└── specs/                       # Architecture specs
# Release plugin (Cargo + npm)
npm run release:plugin patch

# Release server (npm only)
npm run release:server patch

See specs/releasing.md for details.


📚 Documentation


🤝 Contributing

Contributions are welcome! Please:

  1. Follow existing code patterns

  2. Add tests for new features

  3. Update documentation

  4. Ensure npm test and npm run standards pass


Other Notes

This project is tested with BrowserStack.

📄 License

MIT © hypothesi


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.

Available Tools

19 tools
driver_sessionA
Idempotent

[Tauri Apps Only] Start/stop automation session to connect to a RUNNING Tauri app. Supports multiple concurrent app connections - each app runs on a unique port. The most recently connected app becomes the "default" app used when no appIdentifier is specified. Use action "status" to check connection state: returns single app format when 1 app connected, or array format with "isDefault" indicator when multiple apps connected. Action "stop" without appIdentifier stops ALL sessions; with appIdentifier stops only that app. The identifier field (e.g., "com.example.myapp") uniquely identifies each app. REQUIRED before using other webview_* or ipc_* tools. Connects via WebSocket to the MCP Bridge plugin in the Tauri app. For browser automation, use Chrome DevTools MCP instead. For Electron apps, this tool will NOT work.

Inputs: action (required), host, port, appIdentifier.

get_setup_instructionsA
Read-onlyIdempotent

Get instructions for setting up or updating the MCP Bridge plugin in a Tauri project. Call this tool when: (1) driver_session fails to connect, (2) you detect the plugin is not installed or outdated, or (3) the user asks about setup. Returns step-by-step guidance that you should follow to help the user configure their project. IMPORTANT: The instructions require you to examine the project first and ask for permission before making any changes.

Inputs: no named parameters.

ipc_emit_eventA

[Tauri Apps Only] Emit a Tauri event to test event handlers. Requires active driver_session. Events are Tauri-specific (not DOM events). For browser DOM events, use Chrome DevTools MCP instead.

Inputs: eventName (required), payload, appIdentifier.

ipc_execute_commandA

[Tauri Apps Only] Execute Tauri IPC commands (invoke Rust backend functions). Requires active driver_session. This is Tauri-specific IPC, not browser APIs. Plugin commands (plugin:mcp-bridge|*) are routed through the bridge; all other commands are executed via the webview using window.TAURI_INTERNALS.invoke, which keeps the application's Tauri capability rules in force. For Electron IPC or browser APIs, use appropriate tools for those frameworks.

Inputs: command (required), args, windowId, appIdentifier.

ipc_get_backend_stateA
Read-only

[Tauri Apps Only] Get Tauri backend state: app metadata, Tauri version, environment. Requires active driver_session. Use to verify you're connected to a Tauri app and get app info.

Inputs: appIdentifier.

ipc_get_capturedA
Read-only

[Tauri Apps Only] Get captured Tauri IPC traffic (requires ipc_monitor started). Shows captured commands (invoke calls) and events with arguments and responses. For browser network requests, use Chrome DevTools MCP instead.

Inputs: filter, appIdentifier.

ipc_monitorA
Idempotent

[Tauri Apps Only] Monitor Tauri IPC calls between frontend and Rust backend. Requires active driver_session. Captures invoke() calls made through window.TAURI.core. Bridge-internal commands (plugin:mcp-bridge|*) are excluded from capture. This is Tauri-specific; for browser network monitoring, use Chrome DevTools MCP.

Inputs: action (required), appIdentifier.

list_devicesA
Read-only

[Tauri Mobile Apps Only] List Android emulators/devices and iOS simulators. Use for Tauri mobile development (tauri android dev, tauri ios dev). Not needed for desktop-only Tauri apps or web projects.

Inputs: no named parameters.

manage_windowA
Idempotent

[Tauri Apps Only] Manage Tauri windows. Actions: "list" - List all windows with labels, titles, URLs, and state. "info" - Get detailed info for a window (size, position, title, focus, visibility). "resize" - Resize a window (requires width/height, uses logical pixels by default). "focus" - Focus a window (bring to front). "minimize" - Minimize a window. "maximize" - Maximize a window. Desktop-only actions (focus, minimize, maximize) require tauri-plugin-mcp-bridge 0.13.0+ and return a version error on older plugins. Requires active driver_session. For browser windows, use Chrome DevTools MCP instead.

Inputs: action (required), width, height, logical, +2 more.

read_logsA
Read-only

[Tauri Apps Only] Read logs from various sources: "console" for webview JS logs, "android" for logcat, "ios" for simulator logs, "system" for desktop logs. Requires active driver_session for console logs. Use for debugging Tauri app issues at any level.

Inputs: source (required), level, lines, since, +5 more.

webview_dom_snapshotA
Read-only

[Tauri Apps Only] Get a structured DOM snapshot of a Tauri app's webview. Supports different snapshot types for AI consumption. The "accessibility" type returns a YAML representation of the accessibility tree similar to Playwright's aria snapshots, including roles, names, states, and element refs. Use this for understanding UI semantics, finding interactive elements, or accessibility testing. The "structure" type returns a YAML representation of the DOM hierarchy with element tag names, IDs, CSS classes, and data-testid attributes (if present). Use this for understanding page layout, debugging CSS selectors, or locating elements by class/ID. Use the optional selector parameter to scope the snapshot to a subtree. The selector supports CSS (default), XPath, and text content matching via the strategy parameter. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app.

Inputs: type (required), selector, strategy, windowId, +1 more.

webview_execute_jsA

[Tauri Apps Only] Execute JavaScript in a Tauri app's webview context. Requires active driver_session. Has access to window.TAURI. If you need a return value, it must be JSON-serializable. For functions that return values, use an IIFE: "(() => { return 5; })()" not "() => { return 5; }". Accepts an optional timeout parameter (milliseconds) for long-running scripts. Timeout errors will identify which layer timed out (transport, script self-race, or Rust eval). Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app. For browser JS execution, use Chrome DevTools MCP instead.

Inputs: script (required), args, timeout, windowId, +1 more.

webview_find_elementA
Read-only

[Tauri Apps Only] Find elements in a running Tauri app's webview and return their geometry, text, accessible name, attributes, visibility, and optionally their computed styles. Supports CSS selectors (default), XPath expressions, and text content matching via the strategy parameter. The "text" strategy searches element text content (not just direct text nodes), prefers exact matches over substring matches, prefers innermost elements, and prefers interactive ancestors. Returns structured JSON with totalMatches, returned count, and array of matches each containing: nth index, ref ID, tag, trimmed text, accessible name, attributes, bounding rect, visibility, interactability, optional computed styles, and optional truncated outerHTML. Use this instead of webview_execute_js for querySelector, getBoundingClientRect, textContent, and getComputedStyle reads. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app. For browser pages or documentation sites, use Chrome DevTools MCP instead.

Inputs: selector (required), nth, limit, strategy, +5 more.

webview_get_pointed_elementA
Read-only

[Tauri Apps Only] Retrieves element metadata for an element the user previously pointed at via Alt+Shift+Click in the Tauri app. Returns the same rich metadata as webview_select_element (tag, id, classes, attributes, text, bounding rect, CSS selector, computed styles, parent chain) plus an annotated screenshot. The user must Alt+Shift+Click an element first before calling this tool. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app.

Inputs: windowId, appIdentifier.

webview_interactA

[Tauri Apps Only] Click, hover, right-click, scroll, swipe, focus, or perform gestures in a Tauri app webview. Supported actions: click, double-click, long-press, scroll, swipe, focus, hover, right-click. Supports CSS selectors (default), XPath, and text content matching via the strategy parameter. When using a text selector that matches multiple visible elements, you must provide the nth parameter to disambiguate, or the tool will throw an error listing the candidates. Requires active driver_session. For browser interaction, use Chrome DevTools MCP instead.

Inputs: action (required), x, y, nth, +11 more.

webview_keyboardA

[Tauri Apps Only] Type text or send keyboard events in a Tauri app. The selector parameter (for "type" action) supports CSS selectors (default), XPath, and text content matching via the strategy parameter. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app. For browser keyboard input, use Chrome DevTools MCP instead.

Inputs: action (required), key, nth, text, +5 more.

webview_screenshotA
Read-only

[Tauri Apps Only] Screenshot a running Tauri app's webview. Requires active driver_session. Captures only visible viewport. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app. For browser screenshots, use Chrome DevTools MCP instead. For Electron apps, this will NOT work.

Inputs: format, quality, filePath, maxWidth, +3 more.

webview_select_elementA
Read-only

[Tauri Apps Only] Activates an element picker overlay in the Tauri app. The user visually selects an element by clicking it, and the tool returns rich element metadata (tag, id, classes, attributes, text, bounding rect, CSS selector, computed styles, parent chain) plus an annotated screenshot with the element highlighted. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app.

Inputs: timeout, windowId, appIdentifier.

webview_wait_forA
Read-only

[Tauri Apps Only] Wait for elements, text, or IPC events in a Tauri app. When type is "selector", supports CSS (default), XPath, and text strategies via the strategy parameter. Requires active driver_session. Targets the only connected app, or the default app if multiple are connected. Specify appIdentifier (port or bundle ID) to target a specific app. For browser waits, use Chrome DevTools MCP instead.

Inputs: type (required), value (required), timeout, strategy, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 19 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes (interact, keyboard, screenshot, execute_js, IPC commands, window management). The main overlap is among the element-inspection cluster: webview_find_element, webview_dom_snapshot, webview_select_element, and webview_get_pointed_element all return element metadata, and select_element vs get_pointed_element are especially close (both return rich metadata + annotated screenshot), but the descriptions distinguish their invocation mechanisms.

    Naming Consistency4/5

    A predictable verb_noun pattern dominates and domain prefixes (webview_*, ipc_*) group related tools clearly. Minor deviation: a few tools (driver_session, manage_window, list_devices, read_logs) drop the prefix convention, but they remain readable and consistent in style.

    Tool Count4/5

    At 19 tools the surface is on the heavier side but justified by a genuinely broad domain spanning session management, webview automation, IPC inspection, device enumeration, window control, and logging. Each tool maps to a distinct capability rather than padding.

    Completeness4/5

    Coverage is strong: connection lifecycle (driver_session/setup), interaction, keyboard, JS eval, element discovery, screenshots, waits, window control, IPC execution/monitoring/events, and logging. Minor gaps like navigation/history or attribute-only queries are workable via execute_js.

    Maintenance

    ActivityMaintained
    ResponsivenessMostly unanswered

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables AI-driven testing and automation of Tauri desktop applications through natural language, allowing users to interact with UI elements, capture screenshots, execute commands, and test application flows without manual clicking or complex scripts.
      9
      8
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      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.
      14
      2,501 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Tauri plugin that enables AI agents to interact with Tauri applications through screenshots, DOM inspection, and input simulation via the Model Context Protocol. It allows agents to perform actions like clicking, typing, and executing JavaScript within the application's webview context.
      2,501 npm
      1
      MIT