Railway
Enables comprehensive management of Railway infrastructure, including projects, services, variables, and deployments, directly through the Railway GraphQL API. It is designed to work as a remote service over HTTP, allowing seamless integration with c
What is Railway?
Railway is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables comprehensive management of railway infrastructure, including projects, services, variables, and deployments, directly through the railway graphql api. it is designed to work as a remote servi...
Enables comprehensive management of Railway infrastructure, including projects, services, variables, and deployments, directly through the Railway GraphQL API. It is designed to work as a remote service over HTTP, allowing seamless integration with c
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables comprehensive management of Railway infrastructure,
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @railway/mcp-serverManual Installation
npx -y @railway/mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Railway
The Railway MCP server integrates AI assistants with the Railway cloud platform, enabling management of projects, services, deployments, environment variables, and databases through natural language. It works by delegating to the Railway CLI's built-in `railway mcp` command, and supports connections from Claude Code, Cursor, GitHub Copilot, Factory Droid, OpenCode, and Codex. The `@railway/mcp-server` npm package acts as a compatibility shim that automatically invokes the Railway CLI, so the CLI must be installed and authenticated first.
Prerequisites
- Railway CLI installed — run `bash <(curl -fsSL https://railway.com/install.sh)` to install
- A Railway account — sign up free at https://railway.com
- Authenticated Railway CLI — run `railway login` to connect your account
- An MCP-compatible client such as Claude Code, Cursor, or GitHub Copilot
Install the Railway CLI
The Railway CLI is the underlying engine for the MCP server. Install it with the official one-liner.
bash <(curl -fsSL https://railway.com/install.sh)Authenticate the CLI with your Railway account
Log in to your Railway account. This creates a persistent authentication token the MCP server will use.
railway loginInstall the MCP server into your client
Use the Railway CLI's built-in MCP installer. It auto-detects your installed AI tools and merges the Railway entry into their configs without removing other MCP servers.
# Auto-detect and configure all installed MCP clients
railway mcp install
# For a remote hosted server instead of local stdio
railway mcp install --remoteVerify the configuration
Restart your MCP client and ask it to list your Railway projects. A successful response confirms authentication and connectivity.
Manual client configuration (alternative)
If you prefer to configure the client manually rather than using `railway mcp install`, add the JSON config block directly to your MCP client's settings file.
Railway Examples
Client configuration
Manual MCP configuration using the Railway CLI directly. Use this if `railway mcp install` did not auto-configure your client.
{
"mcpServers": {
"railway": {
"command": "railway",
"args": ["mcp"]
}
}
}Prompts to try
Example prompts for managing Railway infrastructure through an AI assistant.
- "List all my Railway projects and their current deployment status"
- "Create a new Railway service called 'api-gateway' in my production project"
- "Set the DATABASE_URL environment variable on my 'backend' service to this connection string"
- "Show me the latest deployment logs for my 'frontend' service"
- "Redeploy the 'worker' service on Railway using the latest commit"Troubleshooting Railway
'railway: command not found' when the MCP client tries to start the server
The Railway CLI must be installed and available in the PATH used by your MCP client. Re-run `bash <(curl -fsSL https://railway.com/install.sh)` and ensure `/root/.railway/bin` (or the install location) is in your PATH. Restart your terminal and MCP client.
Authentication errors when listing projects or making changes
Run `railway login` in your terminal to refresh your credentials. If you recently rotated your Railway API token, the cached credentials may be stale.
MCP client still uses the old `npx -y @railway/mcp-server` configuration
The standalone npm package is now a deprecated shim. While it still works (it calls `railway mcp` internally), update your config to use `"command": "railway", "args": ["mcp"]` directly for better performance and to avoid the npx overhead.
Frequently Asked Questions about Railway
What is Railway?
Railway is a Model Context Protocol (MCP) server that enables comprehensive management of railway infrastructure, including projects, services, variables, and deployments, directly through the railway graphql api. it is designed to work as a remote service over http, allowing seamless integration with c 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/mcp-server. 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.