Mcloud Local logo

Mcloud Local

Organization
medusajs
mcloud-local

Execute mcloud local build to reproduce a Cloud build on the local machine. Use when debugging a build-failed deployment without pushing to the tracked branch, iterating on a build fix, or testing build-variable changes locally. Requires Docker and must run inside the project's Git repo.

Overview

Publishermedusajs
Repositorymedusa-agent-skills
Skill namemcloud-local
Stars
218
Forks
27
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by medusajs on GitHub. Read the source before you install it.

Installation

Install the Mcloud Local AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/medusajs/medusa-agent-skills.git /tmp/medusa-agent-skills
mkdir -p .claude/skills
cp -r /tmp/medusa-agent-skills/plugins/medusa-cloud/skills/mcloud-local .claude/skills/mcloud-local
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcloud Local in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcloud Local on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcloud Local is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cloud CLI: Local Command

Execute mcloud local build to run a Cloud build on the local machine, mirroring how Cloud builds the project. Use it to debug build-failed deployments without pushing changes and waiting for a full Cloud build.

Constraints

  • No --json flag. local build streams plaintext build output and signals the result through its exit code (0 = success). Do not parse its output as JSON.
  • Requires Docker installed and running, and must run from inside the project's Git repository.
  • Reproduces build-failed (build) failures only — not deployment-failed (runtime) failures. For runtime failures, use mcloud logs --deployment <id>.
  • Available since mcloud CLI v0.1.10.
  • The Docker build cache is disabled by default so variable changes always invalidate the cache; pass --docker-cache to enable it.

Command

local build

Run a Cloud build locally. Infers the root path and build variables from the linked Cloud project and environment. Builds the backend by default; pass --type storefront for the storefront.

bash
mcloud local build \
  --organization <org-id> \
  --project <project-id-or-handle> \
  --environment <environment-handle>

Options:

  • -o/--organization <id> — Organization ID (falls back to active context)
  • -p/--project <id-or-handle> — Project ID or handle (falls back to active context)
  • -e/--environment <handle> — Environment whose variables are used (falls back to active context)
  • -t/--type <backend|storefront> — Build type (default: backend)
  • --root-path <path> — Backend root path relative to the repo root (inferred if omitted; . if no Cloud project found)
  • --storefront-path <path> — Storefront path relative to the repo root, for --type storefront (inferred if omitted)
  • --env-file <path> — Use a local .env file instead of the Cloud environment's variables
  • -v/--var <KEY=VALUE> — Override a single build variable; repeatable
  • --docker-cache — Enable the Docker build cache (default: false)

Output:

  • On success (exit 0), the backend image is tagged <repository-name>:cloud-local-build-<commit-hash>; a storefront build writes its output directory and prints the path.
  • On failure (non-zero exit), the command exits with the failing step's error — debug it as you would a Cloud build.

Reproduce a Build Failure

Check out the same commit the failed deployment built so the local build matches, then route on the exit code:

bash
# Identify the failing deployment and the commit it built
DEPLOYMENT_ID=$(
  mcloud deployments list --json \
    | jq -r '[.[] | select(.backend_status == "build-failed")][0].id'
)
COMMIT=$(mcloud deployments get "$DEPLOYMENT_ID" --json | jq -r '.commit_hash')

git checkout "$COMMIT"

if mcloud local build; then
  echo "Build succeeded locally; failure not reproducible from this commit."
else
  echo "Build failed locally; inspect the streamed output for the failing step."
fi

Once the local build exits 0, push the fix to the tracked branch and start a fresh Cloud build with mcloud environments trigger-build <env>.

Examples

bash
# Reproduce the backend build for the active context
mcloud local build

# Reproduce the storefront build
mcloud local build --type storefront --storefront-path apps/storefront

# Test a build-variable fix without editing code
mcloud local build --var NODE_ENV=production

# Build against a local .env file
mcloud local build --env-file .env

# Reuse the Docker cache for a faster rebuild
mcloud local build --docker-cache

Frequently asked questions

What does the Mcloud Local AI skill do?

Execute mcloud local build to reproduce a Cloud build on the local machine. Use when debugging a build-failed deployment without pushing to the tracked branch, iterating on a build fix, or testing build-variable changes locally. Requires Docker and must run inside the project's Git repo.

Why use Mcloud Local on TypingMind?

Because you install it once and use it with any model. Mcloud Local is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcloud Local in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/medusajs/medusa-agent-skills/tree/main/plugins/medusa-cloud/skills/mcloud-local. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcloud Local?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcloud Local?

As many as you like. As long as a model supports skills, you can use Mcloud Local with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcloud Local AI skill free?

It is published on GitHub by medusajs. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇