A command that deploys external MCP plugin servers listed in a marketplace file. MCP servers are services that let an assistant connect to outside tools or data.

Use it to deploy every external server in the marketplace or deploy one named plugin, provided its compose file and Docker Compose are available.

It automates locating the configured server files, choosing the right Docker Compose command, and starting one or all selected services. Missing compose files are reported and skipped instead of stopping the whole deployment.

deploy — Command for Claude Code by jmagar/claude-homelab

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/jmagar/claude-homelab

Made for: Claude Code.

Or install homelab-core, the plugin that ships this one along with the rest of its 18 skills, 5 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jmagar/claude-homelab/deploy/github.svg)](https://agentmods.dev/commands/jmagar/claude-homelab/deploy)

Your own site

<a href="https://agentmods.dev/commands/jmagar/claude-homelab/deploy"><img src="https://agentmods.dev/badge/commands/jmagar/claude-homelab/deploy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jmagar/claude-homelab/deploy"><img src="https://agentmods.dev/badge/commands/jmagar/claude-homelab/deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 446 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00446
Opus 5.5	$0.00006	$0.00178
Sonnet 5.5	$0.00003	$0.00089
Haiku 4.5	$0.00001	$0.00045

Measured 1mo ago against content hash 105f76ba310d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

deploy scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The marketplace lives at: `!cat ~/.claude/plugins/marketplaces/claude-homelab/.claude-plugin/marketplace.json 2>/dev/null || cat ~/claude-homelab/.claude-plugin/marketplace.json`

commands/deploy.md · 39 lines

What it actually says

Deploy MCP plugin servers defined in the homelab marketplace. Arguments (if provided): $ARGUMENTS

The marketplace lives at: !cat ~/.claude/plugins/marketplaces/claude-homelab/.claude-plugin/marketplace.json 2>/dev/null || cat ~/claude-homelab/.claude-plugin/marketplace.json

Instructions

Parse the marketplace to get the list of external plugins (those with source.source == "github"). Extract name and version for each.
Detect docker compose variant:
- docker compose version → use docker compose
- docker-compose version → use docker-compose
- If neither found, report error and stop
Determine which plugins to deploy:
- If $ARGUMENTS is a plugin name (e.g. synapse-mcp), deploy only that one
- If no arguments, deploy all external plugins from the marketplace
For each plugin to deploy:
- Find its compose file at: ~/.claude/plugins/cache/claude-homelab/<name>/<version>/docker-compose.yaml (also check .yml variants)
- Skip tests/ subdirectory compose files
- If compose file not found, warn and skip that plugin — do not stop

Run the deploy from each compose file's parent directory:

cd ~/.claude/plugins/cache/claude-homelab/<name>/<version>
docker compose up --build -d

Report results as a table:
- Plugin name | Status (✓ up / ✗ failed / ⚠ skipped) | Notes
- On any failure: show last 20 lines of that plugin's output
- At the end: run docker compose ps in each successfully deployed directory to show running containers

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 39 lines · 14 tokens per session scan B 105f76ba310d

Subscribe to this mod's changes

deploy is a command published in the GitHub repository jmagar/claude-homelab (86 stars, last pushed 22d ago), licensed MIT. It adds 14 tokens to every session and 446 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code DevOps and cloud LLM agents ai model-context-protocol self-hosted

feature-dev

Guided feature development with codebase understanding and architecture focus.

bearlike/Assistant · 11 tokens

revise-claude-md

Update CLAUDE.md with learnings from this session.

bearlike/Assistant · 11 tokens

code-review

Code review a pull request.

bearlike/Assistant · 5 tokens

expect

Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…

yonatangross/orchestkit · 73 tokens