Railway
Let Claude and Cursor manage your Railway infrastructure through natural language. Deploy, configure, and monitor - autonomously and safely.
What is Railway?
Railway is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to let claude and cursor manage your railway infrastructure through natural language. deploy, configure, and monitor - autonomously and safely.
Let Claude and Cursor manage your Railway infrastructure through natural language. Deploy, configure, and monitor - autonomously and safely.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Let Claude and Cursor manage your Railway infrastructure thr
Use Cases
Maintainer
Works with
Installation
NPM
npx -y railwayManual Installation
npx -y railwayConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Railway
railway-mcp is a Model Context Protocol server that exposes Railway's infrastructure management API to AI assistants like Claude and Cursor, enabling natural-language control over your Railway projects, services, deployments, and databases. Through the server, you can list and create projects, deploy services from GitHub repositories or Docker images, manage environment variables, trigger and monitor deployments, view logs, and provision database services — all without leaving your chat or IDE interface. It is designed for developers who want to manage cloud infrastructure conversationally rather than through the Railway dashboard.
Prerequisites
- Node.js 18 or later
- A Railway account with an API token (obtainable at https://railway.app/account/tokens)
- An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
- Existing Railway projects or permission to create new ones
Get your Railway API token
Log in to Railway and navigate to https://railway.app/account/tokens to generate a new API token. Copy the token — you will need it in the MCP client configuration.
Install via Smithery for Claude Desktop
The quickest way to install railway-mcp for Claude Desktop is via the Smithery CLI, which handles configuration automatically.
npx -y @smithery/cli install @jason-tan-swe/railway-mcp --client claudeOr configure manually in Claude Desktop
Add the railway server block to ~/Library/Application Support/Claude/claude_desktop_config.json, replacing the placeholder with your actual Railway API token.
{
"mcpServers": {
"railway": {
"command": "npx",
"args": ["-y", "@jasontanswe/railway-mcp"],
"env": {
"RAILWAY_API_TOKEN": "your-railway-api-token-here"
}
}
}
}Configure for Cursor or Windsurf
For Cursor, use the Smithery run command with your token passed as a config parameter.
npx -y @smithery/cli@latest run @jason-tan-swe/railway-mcp --config "{\"railwayApiToken\":\"your-railway-api-token\"}"Restart your MCP client and verify
Restart Claude Desktop (or reload your IDE). Ask the assistant to list your Railway projects to confirm the connection is working.
Railway Examples
Client configuration
Manual Claude Desktop configuration for railway-mcp with the required RAILWAY_API_TOKEN environment variable.
{
"mcpServers": {
"railway": {
"command": "npx",
"args": ["-y", "@jasontanswe/railway-mcp"],
"env": {
"RAILWAY_API_TOKEN": "your-railway-api-token-here"
}
}
}
}Prompts to try
Natural-language commands you can give Claude once railway-mcp is connected.
- "List all my Railway projects and their current status"
- "Deploy the GitHub repo github.com/myorg/api as a new Railway service in the production environment"
- "Set the DATABASE_URL environment variable for the api service in my production project"
- "Show me the deployment logs for the last deploy of the frontend service"
- "Provision a PostgreSQL database in my staging environment"
- "What services are running in my production project and when were they last deployed?"Troubleshooting Railway
Authentication errors: 'Invalid API token' or 401 responses
Verify that RAILWAY_API_TOKEN is set to a valid, non-expired token from https://railway.app/account/tokens. Tokens can be revoked from the same page if compromised.
npx cannot find the @jasontanswe/railway-mcp package
Clear the npx cache with npx clear-npx-cache and retry, or install the package globally first with npm install -g @jasontanswe/railway-mcp and change the command to railway-mcp in the config.
Deployment triggered but service stays in 'building' indefinitely
Ask Claude to 'show deployment logs for the stuck service' — the logs usually reveal build errors. Check that your GitHub repository is connected to Railway and that the correct branch is set as the deployment source.
Frequently Asked Questions about Railway
What is Railway?
Railway is a Model Context Protocol (MCP) server that let claude and cursor manage your railway infrastructure through natural language. deploy, configure, and monitor - autonomously and safely. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Railway?
Install via npm with the command: npx -y railway. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Railway?
Railway works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Railway free to use?
Yes, Railway is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Railway Alternatives — Similar Cloud Services Servers
Looking for alternatives to Railway? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Railway in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Railway?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.