Tailscale MCP

🚀 Tailscale MCP Server

A modern Model Context Protocol (MCP) server that provides seamless integration with Tailscale's CLI commands and REST API, enabling automated network management and monitoring through a standardized interface.

🚀 Quick Start

Option 1: NPX (Recommended)

Run directly without installation:

# Explicit package syntax (most reliable)
npx --package=@hexsleeves/tailscale-mcp-server tailscale-mcp-server

# Or install globally
npm install -g @hexsleeves/tailscale-mcp-server
tailscale-mcp-server

Option 2: Docker

# GitHub Container Registry (recommended)
docker run -d \
  --name tailscale-mcp \
  -e TAILSCALE_API_KEY=your_api_key \
  -e TAILSCALE_TAILNET=your_tailnet \
  ghcr.io/hexsleeves/tailscale-mcp-server:latest

# Or use Docker Compose
docker-compose up -d

📖 For detailed Docker usage, development workflows, and deployment strategies, see the Docker Guide

✨ Features

• Device Management: List, authorize, deauthorize, and manage Tailscale devices
• Network Operations: Connect/disconnect, manage routes, and monitor network status
• Security Controls: Manage ACLs, device tags, and network lock settings
• Modern Architecture: Modular tool system with TypeScript and Zod validation
• CLI Integration: Direct integration with Tailscale CLI commands
• API Integration: REST API support for advanced operations

📦 Installation

Available Packages

• NPM: @hexsleeves/tailscale-mcp-server
• Docker Hub: hexsleeves/tailscale-mcp-server
• GitHub Container Registry: ghcr.io/hexsleeves/tailscale-mcp-server

💻 Usage Examples

Configuration

Claude Desktop

Add to your Claude Desktop configuration (~/.claude/claude_desktop_config.json):

Using NPX (Recommended)

{
  "mcpServers": {
    "tailscale": {
      "command": "npx",
      "args": [
        "--package=@hexsleeves/tailscale-mcp-server",
        "tailscale-mcp-server"
      ],
      "env": {
        "TAILSCALE_API_KEY": "your-api-key-here",
        "TAILSCALE_TAILNET": "your-tailnet-name"
      }
    }
  }
}

Using Docker

{
  "mcpServers": {
    "tailscale": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TAILSCALE_API_KEY=your-api-key",
        "-e",
        "TAILSCALE_TAILNET=your-tailnet",
        "ghcr.io/hexsleeves/tailscale-mcp-server:latest"
      ]
    }
  }
}

Environment Variables

Available Tools

Device Management

• list_devices - List all devices in the Tailscale network
• device_action - Perform actions on specific devices (authorize, deauthorize, delete, expire-key)
• manage_routes - Enable or disable routes for devices

Network Operations

• get_network_status - Get current network status from Tailscale CLI
• connect_network - Connect to the Tailscale network
• disconnect_network - Disconnect from the Tailscale network
• ping_peer - Ping a peer device

System Information

• get_version - Get Tailscale version information
• get_tailnet_info - Get detailed network information

📚 Documentation

This project includes comprehensive documentation organized by domain:

• 🔧 CI/CD Workflows - GitHub Actions, testing pipelines, and release automation
• 🧪 Testing Strategy - Unit tests, integration tests, and testing best practices
• 🐳 Docker Guide - Container usage, development workflows, and deployment strategies

🔧 Technical Details

Development

Quick Setup

# Clone and setup
git clone https://github.com/HexSleeves/tailscale-mcp-server.git
cd tailscale-mcp-server
npm install

# Setup environment
cp .env.example .env
# Edit .env with your Tailscale credentials

# Build and run
npm run build
npm start

Development Commands

# Development workflow
npm run dev:direct        # Fast development with tsx
npm run dev:watch         # Auto-rebuild on changes
npm run build:watch       # Build with file watching

# Testing
npm test                  # All tests
npm run test:unit         # Unit tests only
npm run test:integration  # Integration tests (requires Tailscale CLI)
npm run test:watch        # Watch mode

# Quality assurance
npm run qa                # Quick QA (typecheck + unit tests + lint)
npm run qa:full           # Full QA (all tests + checks)
npm run typecheck         # TypeScript validation

# Tools
npm run inspector         # Test with MCP Inspector

Local Claude Desktop Configuration

{
  "mcpServers": {
    "tailscale-dev": {
      "command": "node",
      "args": ["/path/to/your/tailscale-mcp-server/dist/index.js"],
      "env": {
        "TAILSCALE_API_KEY": "your-api-key-here",
        "TAILSCALE_TAILNET": "your-tailnet-name",
        "LOG_LEVEL": "0"
      }
    }
  }
}

📖 For comprehensive development guides, testing strategies, and CI/CD information:

• Testing Documentation - Unit tests, integration tests, coverage
• Docker Development - Container-based development workflows
• CI/CD Workflows - GitHub Actions, automation, releases

Project Structure

src/
├── server.ts              # Main server implementation
├── tools/                 # Modular tool definitions
├── tailscale/             # Tailscale integrations
├── types.ts               # Type definitions
├── logger.ts              # Logging utilities
└── index.ts               # Entry point

Adding New Tools

Create a tool module in src/tools/ and register it in src/server.ts. See existing tools for examples of the modular architecture using Zod schemas and TypeScript.

Debugging

# Enable debug logging
export LOG_LEVEL=0
export MCP_SERVER_LOG_FILE=debug-{timestamp}.log

# View logs
tail -f logs/debug-*.log

API Reference

Tool Categories

Device Tools

• Device listing and filtering
• Device authorization management
• Route management per device

Network Tools

• Network status monitoring
• Connection management
• Peer connectivity testing

Security Tools

• ACL management
• Device tagging
• Network lock operations

🤝 Contributing

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes and add tests
4. Run quality checks: npm run qa:full
5. Commit your changes: git commit -m 'Add amazing feature'
6. Push to the branch: git push origin feature/amazing-feature
7. Open a Pull Request

Development Guidelines

• Use TypeScript for all new code
• Add Zod schemas for input validation
• Include tests for new tools (see Testing Guide)
• Follow the existing modular architecture
• Update documentation for new features

Resources for Contributors

• Testing Strategy - How to write and run tests
• CI/CD Workflows - Understanding the automation pipeline
• Docker Development - Container-based development workflows

📄 License

MIT License - see LICENSE file for details.

🛠️ Support

• Issues - Bug reports and feature requests
• Discussions - Questions and community support
• MCP Documentation - Learn more about MCP

📜 Changelog

See CHANGELOG.md for version history and updates.