Railway MCP Server v2
Enables deployment of applications from GitHub repositories to Railway through the deploy_from_github tool.
Provides comprehensive tools for managing Railway projects, services, and deployments, including creating projects and services, deploying from GitHub repositories, managing environment variables, configuring domains, viewing deployment logs, and controlling service lifecycle operations.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Railway MCP Server v2list my recent deployments for the ecommerce-api service"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Railway MCP Server v2
Railway MCP Server using the official @modelcontextprotocol/sdk with full support for:
Streamable HTTP transport (modern, recommended)
SSE transport (legacy compatibility)
Endpoints
Endpoint | Method | Description |
| POST | Streamable HTTP transport |
| DELETE | Session cleanup |
| GET | SSE transport (legacy) |
| POST | SSE messages endpoint |
| GET | Health check |
Related MCP server: Railway MCP Server
Tools (17 total)
list_projects- List all Railway projectsget_project- Get project detailslist_services- List services in a projectlist_deployments- List deployments for a serviceget_deployment_logs- Get deployment logslist_variables- List environment variableslist_environments- List environments in a projectcreate_project- Create a new Railway projectcreate_service- Create a new servicedeploy_from_github- Deploy from GitHub repocreate_domain- Generate a domain for a serviceset_variable- Set an environment variableset_variables_bulk- Set multiple variables at oncerestart_service- Restart a servicedelete_project- Delete a projectdelete_service- Delete a servicedelete_variable- Delete an environment variable
Environment Variables
RAILWAY_API_TOKEN- Your Railway API token (required)PORT- Server port (default: 3000)
Deploy to Railway
Create a new project in Railway
Connect this GitHub repo
Add environment variable:
RAILWAY_API_TOKENDeploy!
Connect to Claude.ai
Use one of these URLs in Claude.ai Connectors:
Streamable HTTP:
https://your-domain.railway.app/mcpSSE (legacy):
https://your-domain.railway.app/sse
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceEnables AI clients to interact with Letta.ai's stateful agents via cloud deployment on Railway. Provides 20+ tools for agent management, conversations, memory operations, and tool configuration through a streamable HTTP transport optimized for production use.Last updated5MIT
- AlicenseAqualityDmaintenanceEnables management of Railway.app infrastructure through natural language, including deploying services, managing environment variables, monitoring deployments, and controlling project resources.Last updated3672MIT
- AlicenseAqualityDmaintenanceEnables management of Railway.app infrastructure through natural language, including deploying services, managing environment variables, monitoring deployments, and handling databases and volumes.Last updated3672MIT
- AlicenseAqualityDmaintenanceEnables management of Railway.app infrastructure through natural language, allowing users to deploy services, manage environment variables, monitor deployments, and configure projects directly from MCP clients like Claude.Last updated3872MIT
Related MCP Connectors
16 AI-native tools with dual SSE + streamable-http transport. Free tier available.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
The agent-native cloud: database, functions, AI, storage, computers. 55 tools, one API key.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hemichaeli/railway-mcp-server-v2'
If you have feedback or need assistance with the MCP directory API, please join our Discord server