Skip to main content
Glama
rust-debug-mcp

rust-debug-mcp

by ruizrica

rust-debug-mcp

TypeScript Rust Tauri WebSocket Model Context Protocol

A Model Context Protocol (MCP) server for debugging and operating Rust Tauri applications over WebSocket.

Table of Contents

Related MCP server: tauri-plugin-mcp

Overview

rust-debug-mcp bridges MCP clients and Tauri debug backends. It provides a single tool (tauri_debug_command) that routes commands to specialized handlers for app lifecycle operations, core debugging, metrics/task inspection, frontend actions, and UI automation.

It supports multiple target apps through configs/apps.json, including capability checks per app before command execution.

Features

Core Functionality

  • Multi-app registry support with per-app command capability gating

  • App lifecycle management (start_app, kill_app)

  • Core debug command forwarding through a typed WebSocket bridge

  • Response verbosity control (concise and detailed)

Debugging & Inspection

  • Task/session/metrics commands for Commander-style backends

  • Frontend broadcast support for app-side actions

  • UI automation commands (click, fill, select, type, press_key, snapshots, screenshots, wait/hover/scroll, console logs)

Reliability

  • Connection status checks and reconnect behavior in bridge manager

  • Request timeout handling for bridge calls

  • Ordered handler routing with clean command-to-handler resolution

Installation

Quick Setup

# Clone repository
git clone https://github.com/ruizrica/rust-debug-mcp.git

# Enter project
cd rust-debug-mcp

# Install dependencies
npm install

# Build
npm run build

Installing in an MCP Client

Add to your MCP config (example):

{
  "mcpServers": {
    "tauri-debug": {
      "command": "node",
      "args": ["/absolute/path/to/rust-debug-mcp/dist/server.js"],
      "env": {
        "LOG_LEVEL": "info",
        "TAURI_WS_URL": "ws://localhost:9002",
        "COMMANDER_WS_URL": "ws://localhost:9002"
      }
    }
  }
}

For deeper setup and troubleshooting, see docs/RUNBOOK.md.

Usage

Starting the Server

npm run dev
# or
npm start

The server communicates over stdio and is intended to be launched by an MCP client.

Multi-App Configuration

configs/apps.json controls default app, app endpoints, and command capability sets:

{
  "default": "commander",
  "apps": {
    "commander": {
      "name": "Commander",
      "wsUrl": "ws://localhost:9002",
      "commands": ["all"]
    },
    "photon": {
      "name": "Photon CLI",
      "wsUrl": "ws://localhost:9847",
      "commands": ["core", "ui_automation"]
    }
  }
}

Tools API

The server exposes one MCP tool:

Tool

Description

tauri_debug_command

Execute a debug command against a selected app (command, optional params, optional app, optional response_format)

Command Categories

  • App lifecycle: start_app, kill_app

  • Core: test_connection, get_debug_mode, set_debug_mode, get_app_dir, get_logs, get_system_metrics, test_command, simple_test

  • Task/session/metrics: get_session_metrics, get_task_metrics, get_all_tasks, get_task, get_tasks_by_status, get_task_groups, list_windows

  • Frontend action: broadcast_to_frontend

  • UI automation: click, fill, select, type, press_key, get_snapshot, take_screenshot, wait_for, hover, scroll, get_console_logs

For full payload details, see docs/COMMAND_REFERENCE.md.

Examples

Minimal Command

{
  "command": "test_connection"
}

Targeting a Specific App

{
  "command": "get_debug_mode",
  "app": "commander"
}

UI Interaction

{
  "command": "click",
  "app": "photon",
  "params": {
    "uid": "e5"
  }
}

Development

Project Structure

rust-debug-mcp/
├── src/
│   ├── server.ts             # MCP server entry point
│   ├── bridge-manager.ts     # WebSocket bridge and manager
│   ├── app-registry.ts       # Multi-app registry and capability checks
│   ├── handlers/             # Command handlers and router
│   ├── response-formatter.ts # Concise/detailed output formatter
│   └── types.ts              # Type definitions
├── configs/
│   └── apps.json
├── docs/
├── tests/
├── package.json
└── tsconfig.json

Build

npm run build

Typecheck

npm run typecheck

Testing

npm test
npm run test:unit
npm run test:integration

Contributing

Contributions are welcome.

  1. Fork the repository

  2. Create a feature branch

  3. Make and test your changes

  4. Open a pull request

License

MIT


Built with TypeScript, Rust, Tauri, and MCP.

Available Tools

1 tool
tauri_debug_commandA

Debug and inspect Tauri applications via WebSocket.

MULTI-APP SUPPORT: This tool can connect to any Tauri app with a debug WebSocket endpoint.

  • Available apps: commander, photon

  • Default app: commander

  • Use "app" parameter to specify which app to connect to

QUICK REFERENCE:

  • Lifecycle: start_app, kill_app

  • Health: test_connection, get_debug_mode

  • Tasks: get_task, get_tasks_by_status, get_task_metrics, get_all_tasks (Commander only)

  • Sessions: get_session_metrics, list_windows (Commander only)

  • System: get_system_metrics, get_app_dir, get_logs

  • Actions: broadcast_to_frontend, set_debug_mode (Commander only)

  • UI Automation: click, fill, select, type, press_key, get_snapshot, take_screenshot, wait_for, hover, scroll, get_console_logs

FILTERING TASKS (avoid loading all tasks): { "command": "get_task", "params": { "task_id": 123 } } { "command": "get_tasks_by_status", "params": { "status": "working" } } { "command": "get_all_tasks", "params": { "status": "pending", "limit": 20 } } { "command": "get_all_tasks", "params": { "recent_only": true } }

RESPONSE FORMAT: Add response_format: "concise" (default) or "detailed" to control verbosity.

  • concise: Truncates arrays to 20 items, includes metadata about truncation

  • detailed: Returns full data without truncation

APP LIFECYCLE COMMANDS:

  • "start_app": Start a Tauri application (optional: path, command, args, env, timeout, waitForConnection)

  • "kill_app": Kill a running Tauri application (optional: force, timeout)

CORE COMMANDS (all apps):

  • "test_connection": Check Tauri bridge connectivity

  • "get_debug_mode": Get current debug mode status

  • "set_debug_mode": Enable/disable debug mode (requires enabled: boolean)

  • "get_app_dir": Get application directory paths

  • "get_logs": Get recent application logs

  • "get_system_metrics": Get system resource metrics

  • "test_command": Test command execution (requires command: string)

  • "simple_test": Run a simple test command

COMMANDER-SPECIFIC COMMANDS:

  • "get_task": Get single task by ID (requires task_id: number)

  • "get_tasks_by_status": Get tasks filtered by status (requires status: string)

  • "get_all_tasks": Get tasks with optional filtering (status?, limit?, recent_only?)

  • "get_task_metrics": Get task count breakdown by status

  • "get_task_groups": Get task groups/initiatives with progress

  • "get_session_metrics": Get active sessions list

  • "list_windows": List connected WebSocket clients

  • "broadcast_to_frontend": Send message to frontend (requires action, payload)

UI AUTOMATION COMMANDS:

  • "click": Click element (requires uid: string)

  • "fill": Clear and fill input element (requires uid: string, value: string)

  • "select": Select dropdown option (requires uid: string, value: string)

  • "type": Type text into element (requires uid: string, text: string)

  • "press_key": Press keyboard key or combination (requires key: string)

  • "get_snapshot": Get accessibility tree snapshot (returns interactive elements with refs)

  • "take_screenshot": Take page screenshot (optional: full_page: boolean, path: string)

  • "wait_for": Wait for text or element (requires text_or_selector: string, timeout?: number)

  • "hover": Hover over element (requires uid: string)

  • "scroll": Scroll page or element (requires direction: string, amount?: number)

  • "get_console_logs": Get browser/frontend console messages (optional: types[], limit, includePreservedLogs)

EXAMPLES: { "command": "start_app", "app": "photon" } { "command": "start_app", "app": "photon", "params": { "command": "cargo tauri dev", "waitForConnection": true } } { "command": "kill_app", "app": "photon" } { "command": "kill_app", "app": "photon", "params": { "force": true } } { "command": "test_connection" } { "command": "test_connection", "app": "photon" } { "command": "get_task", "params": { "task_id": 42 } } { "command": "get_tasks_by_status", "params": { "status": "working" } } { "command": "get_all_tasks", "params": { "limit": 10 }, "response_format": "detailed" } { "command": "broadcast_to_frontend", "params": { "action": "execute_js", "payload": { "script": "document.title" } } } { "command": "get_snapshot" } { "command": "click", "params": { "uid": "e5" } } { "command": "fill", "params": { "uid": "e3", "value": "test@example.com" } } { "command": "take_screenshot", "params": { "full_page": true } } { "command": "get_console_logs", "params": { "types": ["error", "warn"], "limit": 50 } }

RESPONSE: Returns { success: boolean, data?: unknown, error?: string }

Inputs: command (required), app, params, response_format.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.7/5.0

    Scored across 1 tool

    Disambiguation5/5

    There is only one tool, so there is no possibility of confusing it with another tool. The tool name clearly indicates its purpose, and the internal commands are well-documented.

    Naming Consistency5/5

    With a single tool, naming consistency is inherently satisfied. The name 'tauri_debug_command' is descriptive and follows a clear, consistent pattern.

    Tool Count2/5

    The server exposes only one tool despite covering a broad range of functionality (app lifecycle, tasks, system metrics, UI automation). This is a significant mismatch—the scope warrants multiple focused tools rather than a single oversized one.

    Completeness4/5

    The tool bundles a comprehensive set of commands covering app lifecycle, health checks, system metrics, task management (Commander-specific), sessions, UI automation, and more. It covers the main debugging workflows for Tauri apps, though some task mutation operations are absent, leaving minor gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • 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
      1
      MIT
    • A
      license
      A
      quality
      F
      maintenance
      Rust-based MCP server that lets AI agents natively control and debug Chromium browsers via the Chrome DevTools Protocol (CDP). Single pre-compiled binary, installable with npx @raultov/chrome-debug-mcp, Homebrew or one shell command — no Rust toolchain.
      30
      30 npm
      8
      MIT