Tauri MCP Server
Provides tools for window interaction (screenshot, management, DOM access), user input simulation (mouse, text, JS execution), and data/storage management (localStorage, ping) within Tauri applications.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tauri MCP ServerTake a screenshot of the main window"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tauri Plugin: Model Context Protocol (MCP)
A Tauri plugin and MCP server that enables AI agents (Claude Code, Cursor, etc.) to interact with and debug Tauri desktop applications through standardized interfaces.
Author: Jarad DeLorenzo (@delorenj) Repository: https://github.com/delorenj/tauri-plugin-mcp Homepage: https://delorenj.github.io
Features
The Tauri MCP Plugin provides a comprehensive set of tools that allow AI models and external applications to interact with Tauri applications:
Window Interaction
Take Screenshot: Capture images of any Tauri window with configurable quality and size
Window Management: Control window position, size, focus, minimize/maximize state
DOM Access: Retrieve the HTML DOM content from webviews windows
User Input Simulation
Mouse Movement: Simulate mouse clicks, movements, and scrolling
Text Input: Programmatically input text into focused elements
Execute JavaScript: Run arbitrary JavaScript code in the application context
Data & Storage
Local Storage Management: Get, set, remove, and clear localStorage entries
Ping: Simple connectivity testing to verify the plugin is responsive
Quick Start
Prerequisites
Python 3.12+ - For the build script
Rust & Cargo - For building the Tauri plugin
Bun or npm - For building TypeScript components
Building the Project
This project uses a modern Python build system for managing both artifacts:
# Install Python dependencies
pip install -r requirements.txt
# Build everything (recommended)
python build.py all
# Or build individually
python build.py plugin # Build Rust plugin + JS bindings
python build.py mcp # Build TypeScript MCP serverFor detailed build options and documentation, see BUILD.md.
Legacy Build Commands
If you prefer manual builds:
# Plugin
bun install
bun run build && bun run build-plugin
# MCP Server
cd mcp-server-ts
bun install
bun run buildBasic Configuration
Add to your Claude Code or Cursor MCP settings:
{
"mcpServers": {
"tauri-mcp": {
"command": "node",
"args": ["/path/to/tauri-plugin-mcp/mcp-server-ts/build/index.js"]
}
}
}Related MCP server: MCP Server Tauri
Documentation
Setup Guide - Detailed integration instructions
MCP Server - Available tools and configuration
Mise Environment Setup - Auto-start SSE server with mise
Troubleshooting - Common issues and solutions
Architecture
The plugin uses a multi-layer communication stack:
AI Agent (Claude Code/Cursor)
↓ (MCP Protocol)
MCP Server (Node.js)
↓ (IPC/TCP Socket)
Socket Server (Rust)
↓ (Tauri APIs)
Tauri ApplicationSupports both IPC (Unix sockets/named pipes) and TCP connections for maximum flexibility.
This server cannot be installed
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/delorenj/tauri-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server