|Docs

Railway for Agents

Railway exposes a CLI, a local MCP server, a hosted remote MCP server, and an open agent skills format. AI coding agents can use any of them to deploy services, manage environments, and operate Railway on behalf of a user.

Get set up

Install the Railway CLI and configure agent support — skills, MCP, and authentication — in one command:

If you already have the Railway CLI installed:

Choose your integration

Railway CLI
Deploys, environments, services, logs, and local development from the terminal.
Railway MCP
Local MCP server that runs through the Railway CLI. Best for agent operations on a logged-in machine.
Remote MCP
Hosted MCP server at mcp.railway.com. Browser OAuth, no local CLI required.
Agent Skills
The use-railway skill teaches AI coding agents how to operate Railway. Works with Claude Code, Cursor, Codex, OpenCode, Copilot, and Factory Droid.

When to use each

  • Local MCP — preferred for agent-native operations: project and service discovery, deployment status, bounded logs, variables, domains, templates, metrics, and scoped mutations.
  • Railway CLI — preferred when the task depends on local machine state: current-directory deploys, railway up, railway run, SSH, and local linking.
  • Remote MCP — preferred when the user wants hosted OAuth MCP, or when local CLI configuration is unavailable.
  • Agent Skills — install alongside any of the above so agents arrive with Railway-specific procedural knowledge instead of guessing.