Railway MCP Server

A Model Context Protocol (MCP) server that provides a standardized interface for Large Language Models (LLMs) to interact with the Railway Command Line Interface (CLI).

Features

• Complete Railway CLI Integration: Supports all Railway CLI commands as MCP tools
• Authentication Management: Handles Railway login/logout and user authentication
• State Management: Maintains project and environment context
• Error Handling: Provides structured error messages and clear feedback
• Easy Installation: Available as an NPM package, runnable via npx

Installation

Prerequisites

• Node.js 18.0.0 or higher
• Railway CLI installed and available in your system's PATH

Install Railway CLI

# Install Railway CLI if not already installed
npm install -g @railway/cli

Install MCP Server

# Run directly with npx (recommended)
npx @opichi/server-railway

# Or install globally
npm install -g @opichi/server-railway

Configuration

VS Code with MCP Extension

Add the following to your VS Code settings.json:

{
  "mcpServers": {
    "railway": {
      "command": "npx",
      "args": [
        "-y",
        "@opichi/server-railway"
      ],
      "disabled": false
    }
  }
}

Cursor IDE

Add to your Cursor configuration:

{
  "mcpServers": {
    "railway": {
      "command": "npx",
      "args": [
        "-y",
        "@opichi/server-railway"
      ]
    }
  }
}

Supported Commands

Core Management

• railway_login - Authenticate with Railway
• railway_logout - Log out of Railway account
• railway_whoami - Display current user info
• railway_list - List all Railway projects
• railway_link - Connect directory to Railway project
• railway_unlink - Disconnect from Railway project
• railway_init - Create new Railway project
• railway_delete - Delete a project
• railway_docs - Open Railway documentation
• railway_version - Get Railway CLI version
• railway_help - Get help for specific commands

Deployment & Services

• railway_up - Deploy code to Railway
• railway_down - Remove recent deployment
• railway_logs - Show deployment logs
• railway_add - Add plugin to project
• railway_connect - Connect to database shell
• railway_domain - Manage custom domains
• railway_deploy - Deploy template to project

Environment & Variables

• railway_environment - Manage environments
• railway_variables - Work with environment variables

Local Development

• railway_run - Run command with Railway variables
• railway_shell - Open shell with Railway variables
• railway_status - View project status
• railway_open - Open project in Railway dashboard
• railway_completion - Generate shell completion scripts

Usage Example

Once configured in your MCP-compatible client, you can use natural language to interact with Railway:

"Login to Railway and show me my projects"
"Create a new Railway project called 'my-app'"
"Deploy the current directory to Railway"
"Show me the logs for my latest deployment"
"Set the environment variable DATABASE_URL to my production database"

Error Handling

The server provides clear error messages when:

• Railway CLI is not installed or not found in PATH
• Authentication is required but user is not logged in
• Commands fail due to invalid arguments or Railway API issues
• Network connectivity problems

Development

Setup

git clone <repository-url>
cd railway-mcp-server
npm install

Build

npm run build

Development Mode

npm run dev

Testing

npm test

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues and questions:

• Check the Railway CLI documentation
• Open an issue on GitHub
• Review the MCP specification at Model Context Protocol