Using Medusa Cloud

This handles everything related to Medusa Cloud's CLI tooling, from authentication and deployments to debugging failed builds and managing environment variables. The constraints section alone is worth the read: it's opinionated about always passing `--json` for parsing, confirming context before mutations, and never revealing secrets unless explicitly asked. What makes this practical is the deployment status routing table that tells you exactly which logs to check based on whether your build or runtime failed. It also knows when to load specific reference files depending on your task, so you're not fumbling through docs when a deployment goes sideways at 2am.

skills.sh installs: 1.6K
GitHub stars: 236
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add medusajs/medusa-agent-skills --skill using-medusa-cloud --agent claude-code

Installs into .claude/skills of the current project.

Files

Managing Medusa Cloud Resources

Operational guide for AI agents managing Medusa Cloud infrastructure through the mcloud CLI. Covers setup, deployments, debugging, environments, and variables.

Constraints

Always pass --json when parsing CLI output. Plaintext output is for humans and may change without warning.
Confirm context before mutating. Run mcloud whoami --json before any state change.
Read before you write. Run a get or list before any delete, redeploy, or trigger-build.
Use --yes for destructive operations. delete commands (including variables delete) require --yes in non-interactive mode.
Variable changes need a deploy to apply. variables set/delete don't rebuild or redeploy: redeploy for runtime changes, trigger-build for build changes.
Production environments cannot be deleted. mcloud environments delete errors on production by design.
Never pass --reveal unless the user explicitly asks. Secret values appear in terminal scrollback and logs.
--json and --follow are incompatible. Use bounded time windows (--from/--to) with --json for programmatic log ingestion.