marketplace-mcp-install

marketplace-mcp-install is a skill for Claude Code from ilyautov/marketplaces-mcp-ru. It costs 202 tokens per session (4,776 once invoked), scanned D, original, MIT.

An installation workflow for marketplace-mcp, a local tool connection to seller accounts on Wildberries, Ozon, Yandex Market, and Avito. It is designed to set up the services and API keys for a non-technical seller without manual terminal configuration.

In plain words
What is it for?
Use it to install the marketplace services for Claude Desktop, Claude Code, Codex, or OpenCode and connect seller and advertising accounts.
Why use it?
It removes the need to clone repositories, edit client configuration, create virtual environments, or place API keys by hand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Part of the marketplaces-mcp-ru plugin — 2 skills, 4 MCP servers shipped together

Good fit Use it to install the marketplace services for Claude Desktop, Claude Code, Codex, or OpenCode and connect seller and advertising accounts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install
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.

Any agent
npx skills add ilyautov/marketplaces-mcp-ru --skill marketplace-mcp-install
Clone the repo
git clone --depth 1 https://github.com/ilyautov/marketplaces-mcp-ru

Made for: Claude Code.

Or install marketplaces-mcp-ru, the plugin that ships this one along with the rest of its 2 skills, 4 MCP servers.

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.

agentmods badge for marketplace-mcp-install

README.md
[![agentmods](https://agentmods.dev/badge/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install/github.svg)](https://agentmods.dev/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install)
Your own site
<a href="https://agentmods.dev/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install"><img src="https://agentmods.dev/badge/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install/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.

agentmods 80×15 button for marketplace-mcp-install

Your own site · 80×15
<a href="https://agentmods.dev/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install"><img src="https://agentmods.dev/badge/skills/ilyautov/marketplaces-mcp-ru/marketplace-mcp-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,776 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00202 $0.04776
Opus 5 $0.00101 $0.02388
Sonnet 5 $0.00040 $0.00955
Haiku 4.5 $0.00020 $0.00478

Measured today against content hash 5871d5a7711f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

marketplace-mcp-install scanned grade D with 3 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 today.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Что внутри: MCP-серверы `wb` (Wildberries Seller API), `ozon` (Ozon Seller API), `yandex` (Yandex Market Partner API), `avito` (Avito API для бизнеса), плюс опциональный `ozon-perf` (рекламный кабинет Ozon Performance).

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

> `git clone … /tmp/mmru && rm -rf /tmp/mmru/.git && cp -R /tmp/mmru/. <папка>/`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- macOS/Linux: `cd ~ && curl -L <RELEASE_ZIP_URL> -o mm.zip && unzip mm.zip`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

marketplace-mcp-install/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Установка marketplaces-mcp-ru (WB, Ozon, Яндекс Маркет, Авито) под не-технического продавца

Цель скилла: пользователь сказал «поставь мне WB и Ozon MCP» — и через несколько минут в его ИИ-клиенте появились инструменты для работы с кабинетом селлера, без ручного редактирования JSON и без pip install. Зависимости ставит сам serve.py при первом запуске (локальный venv).

Репозиторий: https://github.com/ilyautov/marketplaces-mcp-ru (опубликован, есть Releases).

Главный путь — «скинул репо → агент поставил»: пользователь подключает папку с репозиторием в Cowork (или она уже на машине), агент запускает install.py — тот копирует приложение в стабильное место ~/.marketplace-mcp/app и указывает конфиг туда. Поэтому подключённую/скачанную папку потом можно перемещать или удалять — MCP не сломается. Остальные пути (склонируй сам, pip) — для тех, кто хочет повозиться руками.

Что внутри: MCP-серверы wb (Wildberries Seller API), ozon (Ozon Seller API), yandex (Yandex Market Partner API), avito (Avito API для бизнеса), плюс опциональный ozon-perf (рекламный кабинет Ozon Performance). Ключи хранятся локально в ~/.marketplace-mcp/cabinets.json (chmod 600), НЕ в конфиге клиента и НЕ в репозитории.


Шаг 0 — ОПРЕДЕЛИ СРЕДУ (это критично, не пропускай)

От среды зависит, что ты можешь сделать сам, а что — только провести пользователя за руку. Будь честен про границу: НЕ обещай того, что среда физически не может.

Ты в Claude Code (или другом локальном CLI, где bash = реальная машина пользователя)

Здесь bash выполняется НА машине пользователя. Ты можешь сделать ВСЁ автоматически:

  • склонировать/скачать репозиторий,
  • запустить python3 install.py --client claude-code (или нужного клиента),
  • помочь собрать ключи и сохранить кабинет,
  • проверить установку serve.py ... --selfcheck.

Проверка среды: запусти pwd && uname -a && whoami. Если это домашняя папка пользователя на его ОС (macOS/Windows/Linux), а не контейнер — ты локально. Иди по шагам 1→4 сам.

Read the full file on GitHub · 235 lines

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.

  1. today Changed · +20 tokens per session 5871d5a7711f
  2. yesterday First seen · 235 lines · 182 tokens per session scan D 3aad13936699

Subscribe to this mod's changes

marketplace-mcp-install is a skill published in the GitHub repository ilyautov/marketplaces-mcp-ru (26 stars, last pushed today), licensed MIT. It adds 202 tokens to every session and 4,776 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.