Railway MCP Server
Enables interaction with Railway cloud platform through the CLI to manage projects, services, deployments, and environments. Supports creating projects, deploying templates, managing environment variables, and monitoring logs through natural language commands.
README
Railway MCP Server (Experimental)
A Model Context Protocol (MCP) server for interacting with your Railway account. This is a local MCP server provides a set of opinionated workflows and tools for managing Railway resources.
[!IMPORTANT] This is an experimental project (like really experimental). You should expect bugs and missing features. The MCP server doesn't include destructive actions by design, that said, you should still keep an eye on which tools and commands are being executed.
Prerequisites
The Railway CLI is required for this server to function.
Installation
Cursor
Add the following configuration to .cursor/mcp.json
{
"mcpServers": {
"railway-mcp-server": {
"command": "npx",
"args": ["-y", "@railway/mcp-server"],
}
}
}
VS Code:
Add the following configuration to .vscode/mcp.json
{
"servers": {
"railway-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@railway/mcp-server"],
}
}
}
Example Usage
Creating a new project, deploying it, and generating a domain
Create a Next.js app in this directory and deploy it to Railway. Make sure to also assign it a domain. Since we're starting from scratch, there is no need to pull information about the deployment or build for now
Deploy a from a template (database, queue, etc.). Based on your prompt, the appropriate template will be selected and deployed. In case of multiple templates, the agent will pick the most appropriate one. Writing a detailed prompt will lead to a better selection. Check out all of the available templates.
Deploy a Postgres database
Deploy a single node Clickhouse database
Pulling environment variables
I would like to pull environment variables for my project and save them in a .env file
Creating a new environment and setting it as the current linked environment
I would like to create a new development environment called `development` where I can test my changes. This environment should duplicate production. Once the environment is created, I want to set it as my current linked environment
Available MCP Tools
The Railway MCP Server provides the following tools for managing your Railway infrastructure:
check-railway-status- Checks that the Railway CLI is installed and that the user is logged in- Project Management
list-projects- List all Railway projectscreate-project-and-link- Create a new project and link it to the current directory
- Service Management
list-services- List all services in a projectlink-service- Link a service to the current directorydeploy- Deploy a servicedeploy-template- Deploy a template from the Railway Template Library
- Environment Management
create-environment- Create a new environmentlink-environment- Link an environment to the current directory
- Configuration & Variables
list-variables- List environment variablesset-variables- Set environment variablesgenerate-domain- Generate a railway.app domain for a project
- Monitoring & Logs
get-logs- Retrieve build or deployment logs for a service
Development
Prerequisites
- Node.js >= 20.0.0
- pnpm >= 10.14.0
-
Clone the repository
git clone https://github.com/railwayapp/railway-mcp-server.git cd railway-mcp-server -
Install dependencies
pnpm install -
Start the development server
pnpm devThis command will generate a build under
dist/and automatically rebuild after making changes. -
Configure your MCP client
Add the following configuration to your MCP client (e.g., Cursor, VSCode) and replace
/path/to/railway-mcp-server/dist/index.jswith the actual path to your built server.Cursor:
.cursor/mcp.json{ "mcpServers": { "railway-mcp-server": { "command": "node", "args": ["/path/to/railway-mcp-server/dist/index.js"], } } }VSCode:
.vscode/mcp.json{ "servers": { "railway-mcp-server": { "type": "stdio", "command": "node", "args": ["/path/to/railway-mcp-server/dist/index.js"], } } }
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。