MCP Catalogs
Home

tauri-plugin-mcp

by P3GLEG·96·Score 48

Tauri plugin enabling AI agents to debug applications through screenshots, DOM access, and input simulation.

developer-toolsbrowser-automationproductivity
27
Forks
9
Open issues
this month
Last commit
2d ago
Indexed

Overview

Tauri-plugin-mcp is a comprehensive solution that bridges AI agents like Cursor and Claude Code with Tauri applications through the Model Context Protocol. It provides 10 powerful tools including screenshot capture, DOM inspection, input simulation, window management, and JavaScript execution, enabling AI to interact with and debug Tauri apps in real-time. The plugin supports both IPC and TCP connections with proper authentication and security measures.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Automated UI testing and debugging of Tauri applications by AI agents
you:Visual regression testing and automated bug reporting in desktop apps
you:AI-powered development assistance for cross-platform desktop applications
you:Which AI agents support this MCP server?
you:What platforms are supported?

When to choose this

Choose this when you need AI-powered debugging and interaction specifically for Tauri applications, especially during development workflows.

When NOT to choose this

Don't choose this if you're not using Tauri, or if you need cross-desktop debugging capabilities beyond what Tauri provides.

Tools this server exposes

10 tools extracted from the README
  • take_screenshot

    Captures a screenshot of an application window.

  • query_page

    Inspects the current page with various modes.

  • click

    Clicks at x/y coordinates or via selector.

  • type_text

    Types text into the page with various targeting options.

  • mouse_action

    Performs non-click mouse actions like hover, scroll, or drag.

  • navigate

    Controls webview navigation to different URLs.

  • execute_js

    Runs arbitrary JavaScript in the webview.

  • manage_storage

    Handles localStorage and cookie operations.

  • manage_window

    Controls window state, size, and zoom level.

  • wait_for

    Waits for a condition like text or element visibility.

Comparable tools

electron-debug-mcpwebview-debug-toolsplaywright-mcp

Installation

Installation

  1. **Install the Tauri plugin**:
npm install tauri-plugin-mcp
  1. **Register the plugin in your Tauri app**:
#[cfg(debug_assertions)]
{
    builder = builder.plugin(tauri_plugin_mcp::init_with_config(
        tauri_plugin_mcp::PluginConfig::new("APPLICATION_NAME".to_string())
            .start_socket_server(true)
            .socket_path("/tmp/tauri-mcp.sock")
    ));
}
  1. **Configure your AI agent** (e.g., Claude Desktop):
{
  "mcpServers": {
    "tauri-mcp": {
      "command": "npx",
      "args": ["tauri-plugin-mcp-server"]
    }
  }
}

FAQ

Which AI agents support this MCP server?
Currently, Cursor and Claude Code are explicitly mentioned as supported. Any agent implementing the MCP protocol can potentially connect.
What platforms are supported?
The plugin supports macOS (native input injection), Windows/Linux (JS-based input fallback), with screenshot support on all three platforms.

Compare tauri-plugin-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.