What is deploy-mcp-server?

A skill for deploying an existing MCP server, a service that lets compatible AI tools call external capabilities, to a remote Linux server over SSH. It also sets up automatic updates, a system service, a Caddy reverse proxy, and HTTPS certificates.

Use it to publish an MCP server, run it as a Linux service, pull updates from Git, expose it through Caddy, and enable automatic TLS certificates from Let's Encrypt.

It turns deployment and ongoing updates into a defined process, while keeping server connection details in a separate configuration file.

How Bazilio-san/mcp-vkusvill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Bazilio-san/mcp-vkusvill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Bazilio-san/mcp-vkusvill/master/.claude/skills/deploy-mcp/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Bazilio-san/mcp-vkusvill

Made for: Claude Code.

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/skills/bazilio-san/mcp-vkusvill/deploy-mcp/github.svg)](https://agentmods.dev/skills/bazilio-san/mcp-vkusvill/deploy-mcp)

Your own site

<a href="https://agentmods.dev/skills/bazilio-san/mcp-vkusvill/deploy-mcp"><img src="https://agentmods.dev/badge/skills/bazilio-san/mcp-vkusvill/deploy-mcp/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/skills/bazilio-san/mcp-vkusvill/deploy-mcp"><img src="https://agentmods.dev/badge/skills/bazilio-san/mcp-vkusvill/deploy-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,772 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00161	$0.02772
Opus 5.5	$0.00064	$0.01109
Sonnet 5.5	$0.00032	$0.00554
Haiku 4.5	$0.00016	$0.00277

Measured 2mo ago against content hash d5d5554c7ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deploy-mcp-server scanned grade A with 0 findings 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check-server.cjs, scripts/deploy-lib.cjs, scripts/deploy.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/deploy-mcp/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Развёртывание MCP-сервера на удалённый сервер

Скилл разворачивает уже существующий проект MCP-сервера (на базе fa-mcp-sdk) на удалённый Linux-сервер, запускает его как системную службу и настраивает ежеминутное автообновление из git-репозитория. Публикация наружу выполняется через обратный прокси Caddy с автоматическим выпуском TLS-сертификата Let's Encrypt.

Все вспомогательные скрипты лежат в ${CLAUDE_SKILL_DIR}/scripts/ и запускаются через node.

Главное правило: вся конкретика — в deploy.yaml

В этом файле SKILL.md намеренно нет ни адресов серверов, ни доменов, ни путей, ни ключей. Любые реквизиты подключения скрипты читают из файла deploy.yaml в корне проекта. Шаблон со всеми пояснениями находится рядом: ${CLAUDE_SKILL_DIR}/deploy.example.yaml.

Если deploy.yaml отсутствует — попросите пользователя скопировать шаблон в корень проекта и заполнить его, либо помогите заполнить, задавая вопросы обычной прозой (адрес сервера, пользователь, путь к ключу, домен). Файл deploy.yaml содержит секреты и обязан быть в .gitignore (строка /deploy.yaml).

Что задаётся в deploy.yaml

Часть значений можно не указывать — скрипт выводит их сам:

ssh.host, ssh.user, ssh.key — доступ по SSH (обязательно).
paths.projectDir — каталог проекта на сервере (обязательно). paths.nodeProjectsDir можно не задавать — берётся родительский каталог projectDir.
git.sshUrl — можно оставить пустым: формируется из package.json → repository.url, где https-адрес преобразуется в SSH-адрес вида git@host:owner/repo.git (клонирование на сервере идёт по SSH).
git.branch — по умолчанию master.
node.version — можно не задавать: берётся из .envrc (nvm use <версия>).
service.name — по умолчанию package.json → name. service.port — по умолчанию config/default.yaml → webServer.port.
domain.name, domain.upstream — если домен не задан, публикация через Caddy пропускается, сервис остаётся доступен только локально на сервере.
deploy.email — адрес для писем об автообновлении (пусто — письма не шлются).

Read the full file on GitHub · 158 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 158 lines · 161 tokens per session scan A d5d5554c7ab8

Subscribe to this mod's changes

deploy-mcp-server is a skill published in the GitHub repository Bazilio-san/mcp-vkusvill (1 stars, last pushed 4mo ago), licensed MIT. It adds 161 tokens to every session and 2,772 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cloud DevOps and cloud

deploy-mcp-server next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deploy-mcp-serverBazilio-san/mcp-vkusvill	Skill	1	4mo ago	MIT	A	161	Claude Code
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	171	Claude Code, Codex
cloud-architectJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	71	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code

mcp-vkusvill: Skill for Claude Code