Aerostack
Aerostack
electrical_services

Railway MCP Server — Hosted Ai Integration

MCP Server language Hosted language Public

Deploy services, inspect logs, manage environments, and control your Railway infrastructure with AI.

aerostack @aerostack verified
• v0.1.0 • MIT • Updated Jun 28, 2026
add_circleAdd to Workspace
robot_2

Use with AI AssistantsMCP

Connect Claude, Cursor, or any MCP-compatible client — then call tools directly

① Add This MCP Server

Paste into your AI client config — then all its tools are available instantly.

.claude/mcp.json
{
  "mcpServers": {
    "railway": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-railway",
      "headers": {
        "Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
      }
    }
  }
}

Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.

② Call a Tool

Ask your AI assistant to call a specific tool, or send raw JSON-RPC:

+2 more

Natural Language Prompt

“Use the _ping tool to verify railway credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”

Using a Workspace?

Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.

add_circleAdd to Workspace

description Overview

mcp-railway — Railway MCP Server

Manage Railway projects, services, deployments, and logs from your AI agents.

Railway is the developer-friendly cloud platform for deploying backends, databases, and services with zero infrastructure configuration. This MCP server connects your AI agents to the Railway API — letting them inspect projects, check deployment health, stream logs, review environment variables, and trigger redeploys, all from natural language without opening the Railway dashboard.

Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-railway

What You Can Do

  • Check deployment status across all Railway services to quickly identify what's failing or outdated
  • Stream deployment logs to diagnose production issues without leaving your chat interface
  • Trigger redeploys for any service in any environment to roll out a fix or restart a crashed container
  • Inspect environment variables for a service to verify configuration without granting dashboard access

Available Tools

Tool Description
list_projects List all Railway projects for the authenticated user
get_project Get project details including environments and services
list_services List services in a Railway project
list_deployments List recent deployments for a service (last 10)
get_deployment_logs Get logs for a specific deployment
list_variables List environment variables for a service in an environment
redeploy_service Trigger a redeploy of a service in an environment

Configuration

Variable Required Description How to Get
RAILWAY_API_TOKEN Yes Railway API token for GraphQL API authentication railway.com/account/tokens → Create Token → give it a name → copy the token

Quick Start

Add to Aerostack Workspace
  1. Go to aerostack.dev → Your Project → MCPs
  2. Search for "Railway" and click Add to Workspace
  3. Add your RAILWAY_API_TOKEN under Project → Secrets

Once added, every AI agent in your workspace can call Railway tools automatically — no per-user setup needed.

Example Prompts
"List all my Railway projects and show the status of the most recent deployment for each"
"Get the last 100 log lines for the api-service deployment that failed 20 minutes ago"
"Redeploy the worker service in the production environment on the my-app project"
Direct API Call
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-railway \
  -H 'Content-Type: application/json' \
  -H 'X-Mcp-Secret-RAILWAY-API-TOKEN: your-api-token' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_projects","arguments":{}}}'

License

MIT

terminal Tools (8)

Available tools on this MCP server. Each tool can be called directly from any AI agent.

terminal
_ping #1

Verify Railway credentials by calling a lightweight read endpoint. Used internally by Aerostack to validate credentials.

terminal
list_projects #2

List all Railway projects for the authenticated user

terminal
get_project #3

Get details of a Railway project including environments and services

terminal
list_services #4

List services in a Railway project

terminal
list_deployments #5

List recent deployments for a Railway service (last 10)

terminal
get_deployment_logs #6

Get logs for a specific Railway deployment

terminal
list_variables #7

List environment variables for a service in a specific environment

terminal
redeploy_service #8

Trigger a redeploy of a Railway service in a specific environment

Details

upgrade Version 0.1.0
gavel License MIT
wifi Transport streamable-http
lock Access Public
category Category AI
terminal Tools 8

language Live Endpoint

https://mcp.aerostack.dev/s/aerostack/mcp-railway

Sub-50ms globally · Zero cold start

Publisher

aerostack
@aerostack verified

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

Tags

devops deployment infrastructure railway hosting
Browse more servers

More in AI

Browse AI MCPs →
hub

Canva Design Platform

by @aerostack

Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP

ai
star 0
hub

Intercom Messaging

by @aerostack

Conversations, contacts, tickets, articles via Intercom's official MCP

ai
star 0
hub

Anthropic

by @aerostack

Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.

ai
star 0
hub

Vercel Deployments

by @aerostack

Deployments, projects, domains, env vars, logs via Vercel's official MCP

ai
star 0
hub

Gmail

by @aerostack

Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.

ai
star 0
hub

Mailchimp

by @aerostack

Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.

ai
star 0

Frequently asked questions

What is the Railway MCP server and what can it do? +

The Railway MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `list_projects`, `get_project`, `list_services`, `list_deployments`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.

Is the Railway MCP server hosted, or do I have to run it myself? +

It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.

Which AI agents and editors can use the Railway MCP server? +

Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same Railway MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.

How do I install the Railway MCP server in Claude Desktop? +

Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-railway": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-railway"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.

How do I use the Railway MCP server in Cursor? +

In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-railway", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-railway"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.

Does Railway MCP require authentication? +

Yes. Railway requires authentication. Check the MCP's documentation for the required credentials.