Railway MCP

- Local MCPruns through theRailway CLIon your machine and uses local CLI context.
- Remote MCPruns atmcp.railway.com. Connect directly using OAuth, or runrailway mcp proxyto reuse credentials from yourrailway loginsession.

Install the Railway CLI and configure agent skills, MCP, and authentication in one command. Select the options to generate the setup command:

If the CLI is already installed, skip the bootstrap and run:

railway setup agent # Local MCP railway setup agent --remote # Remote MCP through the CLI proxy railway setup agent --remote --oauth # Remote MCP with OAuth

Read on for per-editor manual configuration, the available tool list, and security considerations.

If you'd rather configure an editor manually, or want to inspect whatrailway mcp installwrites, use the selector to switch between local stdio, Remote MCP through the CLI proxy, and Remote MCP with OAuth:

railway mcp installmerges the Railway server entry into existing configs without removing other MCP servers. Re-run it any time to update.

TheModel Context Protocol (MCP)defines a standard for how AI applications (hosts) can interact with external tools and data sources through a client-server architecture.

- Hosts: Applications such as Cursor, VS Code, Claude Code, or Windsurf that connect to MCP servers.
- Clients: The layer within hosts that maintains one-to-one connections with individual MCP servers.
- Servers: Standalone programs (like the Railway MCP Server) that expose tools and workflows for managing external systems.

The Local MCP server translates natural language requests into CLI workflows powered by theRailway CLI. Remote MCP runs on Railway's infrastructure and supports OAuth. The CLI proxy provides another connection path by passing credentials from yourrailway loginsession to Remote MCP.

The server and authentication method determine which local tools and credentials you need.

Use prompts that describe the Railway outcome you want the agent to produce.

Create a Next.js app in this directory and deploy it to Railway. Also assign it a domain.

Pull environment variables for my project and save them to a .env file

Debug a failing deployment(remote-onlyrailway-agenttool)

Use the railway agent to figure out why my backend service is crashing on deploy

Redeploy my api service in the production environment

List feature flags for project <projectId>

Set the checkout-v2 feature flag to true on project <projectId>

The Railway MCP Server exposes the following tools. Your AI assistant selects tools based on your request.

Local MCP runs through the Railway CLI and exposes these tools:

- Account:whoami
- Projects and services:list_workspaces,list_projects,create_project,list_services,create_service,remove_service,connect_service_source,disconnect_service_source,link_service,get_service_config,update_service, andscale_service
- Environments and deployments:create_environment,link_environment,environment_status,list_deployments, anddeploy
- Variables:list_variables,set_variables, andadd_reference_variable
- Domains:generate_domain,list_domains,domain_status,update_domain,delete_domain, andretry_domain_certificate
- Networking:list_tcp_proxies,get_tcp_proxy,create_tcp_proxy,remove_tcp_proxy,private_network_status, andprivate_network_update
- Templates:search_templatesanddeploy_template
- Storage:create_bucket,remove_bucket,create_volume,update_volume, andremove_volume
- Observability:get_logs,service_metrics,http_requests,http_error_rate, andhttp_response_time
- Documentation:docs_searchanddocs_fetch

Remote MCP exposes the following tools. Userailway-agentfor multi-step operations.

- list-projects,create-project,list-services

- list-feature-flags,get-feature-flag
- set-feature-flag,delete-feature-flag(admin; destructive delete is marked at the protocol level)

- redeploy
- accept-deploy: commit staged changes and deploy (destructive; clients prompt for confirmation)

- railway-agent: hand a natural-language request to Railway's AI agent for multi-step operations like log analysis, debugging, and service configuration

The Railway MCP Server runs CLI commands or invokes Railway APIs on your behalf. Local MCP marks destructive tools with protocol-level hints and returns a preview before requiringconfirm: true. You should still:

- Review actionsrequested by the LLM before approving them, especially destructive ones (remove_service,delete_domain,remove_tcp_proxy,remove_bucket,remove_volume,redeploy,accept-deploy, andrailway-agent).
- Restrict accessto ensure only trusted users can invoke the MCP server.
- Avoid production risksby limiting usage to non-critical environments where possible.

- CLI proxy authentication.The proxy reads and refreshes yourrailway logincredentials. Editor configuration doesn't contain a long-lived Railway credential.
- OAuth scoping.With direct OAuth, you choose which workspaces and projects the client can access. Tokens are short-lived and can be revoked from your Railway account settings.
- Destructive actionsare marked at the protocol level. Clients that respect these hints will prompt for confirmation.
- Project tokens are not accepted.Remote MCP requires a user identity for billing and audit trails.

Railway runs an official remote MCP server — connect over a hosted URL instead of installing this one locally.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

The Shipyard CLI provides an MCP server for agents to manage Shipyard environments directly: by pulling logs, comparing branches, running tests, and stopping/starting environments..

A Nix-based configuration framework for deploying MCP servers with ready-to-use packages, supporting modular and reproducible builds.

Paid remote MCP for Skybridge, structured receipts, usage logs, and audit-ready JSON evidence.

All Azure MCP tools in a single server. The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. Azure MCP Server can be used alone or with the GitHub Copilot for Azure extension in VS Code.

Access and interact with Harness platform data, including pipelines, repositories, logs, and artifact registries.

An SSE-based MCP server that allows LLM-powered applications to interact with OCI registries. It provides tools for retrieving information about container images, listing tags, and more.

The Octopus MCP Server provides your AI assistant with powerful tools that allow it to inspect, query, and diagnose problems within your Octopus instance, transforming it into your ultimate DevOps wingmate.

Secure virtual machines for agents hosted by Superserve