Railway
Railway's official MCP server that provides AI assistants with comprehensive Railway platform management capabilities through both CLI integration and direct API access. The implementation wraps Railway CLI commands for core operations like project creation, service deployment, environment management, and log retrieval, while also integrating with Railway's GraphQL API for advanced features like template deployment from Railway's template library. Built with TypeScript and designed as an experimental tool, it enables conversational workflows for deploying applications, managing infrastructure, setting environment variables, and monitoring deployments without manual CLI usage, making it valuable for developers who want to manage their Railway projects through natural language interactions while maintaining the full power of Railway's deployment platform.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/railwayapp/railway-mcp-server
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Railway from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.