yandex-direct

yandex-direct is a skill for Claude Code from nikolaymokh-dev/yandex-direct-mcp. It costs 55 tokens per session (4,068 once invoked), scanned A, a copy of yandex-direct, MIT.

A guide for controlling Yandex.Direct, an online advertising platform, through MCP tools. It covers authentication and the supported operations for campaigns, ads, keywords, bids, audiences, budgets, and statistics.

In plain words
What is it for?
Use it to check authentication, manage Yandex.Direct campaigns and ads, edit keywords and bids, work with targeting, adjust budgets, or retrieve advertising statistics.
Why use it?
It helps an assistant authenticate correctly and use the current tool names and workflow instead of relying on outdated commands or starting advertising operations before login is complete.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the yandex-direct plugin — 3 skills, 1 hook, 1 MCP server shipped together

Good fit Use it to check authentication, manage Yandex.Direct campaigns and ads, edit keywords and bids, work with targeting, adjust budgets, or retrieve advertising statistics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct
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 nikolaymokh-dev/yandex-direct-mcp --skill yandex-direct
Clone the repo
git clone --depth 1 https://github.com/nikolaymokh-dev/yandex-direct-mcp

Made for: Claude Code.

Or install yandex-direct, the plugin that ships this one along with the rest of its 3 skills, 1 hook, 1 MCP server.

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 yandex-direct

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct/github.svg)](https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct)
Your own site
<a href="https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct"><img src="https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct/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 yandex-direct

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct"><img src="https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/yandex-direct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,068 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 97% copy Near-identical to another mod 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 $0.00055 $0.04068
Opus 5 $0.00028 $0.02034
Sonnet 5 $0.00011 $0.00814
Haiku 4.5 $0.00006 $0.00407

Measured 10d ago against content hash aede60d52900, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yandex-direct 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 10d 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.

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.

Origin

This is a copy

97% identical to yandex-direct — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/yandex-direct/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Яндекс.Директ — управление через MCP tools

Управление рекламными кампаниями в Яндекс.Директ через MCP-инструменты плагина.

Первое действие — проверь авторизацию

Всегда начинай с auth_status(). Если valid: false:

  1. Вызови auth_login() — он покажет ссылку для авторизации и запросит код через форму
  2. Пользователю не нужно ничего знать заранее — flow полностью интерактивный
  3. После авторизации токен сохраняется на диск, повторный логин не требуется

Не пытайся вызывать другие tools пока авторизация не пройдена — они вернут ошибку.

Доступный MCP-контракт (146 tools)

Контракт теперь следует иерархии:

MCP -> direct (package: direct-cli) -> tapi-yandex-direct -> Yandex.Direct API

  • Используй только публичные MCP tools.
  • Не опирайся на старые alias-имена (*_list, agency_clients_*, keyword_bids_*, smart_targets_* и т.д.).
  • Для Direct-операций используй канонические имена service_method.
  • v4 Live методы вызывай только через публичные MCP tools; shell-группы без CLI-команд не используются.

Правила именования

  • *_list*_get: campaigns_get, ads_get, keywords_get
  • Имена сервисов совпадают с direct: agencyclients_*, audiencetargets_*, keywordbids_*, smartadtargets_*, dynamicads_*, negativekeywordsharedsets_*, turbopages_get
  • CLI методы с дефисом становятся snake_case:
    • changes_check_campaigns
    • changes_check_dictionaries
    • keywordsresearch_has_search_volume
    • bids_set_auto
    • keywordbids_set_auto
    • audiencetargets_set_bids
    • dynamicads_set_bids
    • smartadtargets_set_bids

Direct API tools — основные семейства

Семейство Канонические tools
Кампании campaigns_get/add/update/delete/archive/unarchive/suspend/resume
Группы / объявления / ключи adgroups_get/add/update/delete, ads_get/add/update/delete/moderate/suspend/resume/archive/unarchive, keywords_get/add/update/delete/suspend/resume/archive/unarchive
Ставки keywordbids_get/set/set_auto, bids_get/set/set_auto, bidmodifiers_get/add/set/delete
Таргетинг audiencetargets_get/add/delete/suspend/resume/set_bids, retargeting_get/add/update/delete, dynamicads_get/add/delete/suspend/resume/set_bids, dynamicfeedadtargets_get/add/delete/suspend/resume/set_bids, smartadtargets_get/add/update/delete/suspend/resume/set_bids
Стратегии strategies_get/add/update/archive/unarchive
Медиа и расширения adimages_get/add/delete, advideos_get/add, adextensions_get/add/delete, sitelinks_get/add/delete, vcards_get/add/delete, creatives_get/add
Справочники / изменения / отчёты dictionaries_get, dictionaries_get_geo_regions, changes_check, changes_check_campaigns, changes_check_dictionaries, reports_get
v4 Live balance_get, v4account_get_accounts, v4account_update_account, v4account_deposit, v4account_invoice, v4account_transfer_money, v4account_enable_shared_account, v4events_get_events_log, v4goals_get_stat_goals, v4goals_get_retargeting_goals, v4tags_get_campaigns, v4tags_get_banners, v4tags_update_campaigns, v4tags_update_banners, v4forecast_create, v4forecast_list, v4forecast_get, v4forecast_delete, v4wordstat_create_report, v4wordstat_list_reports, v4wordstat_get_report, v4wordstat_delete_report
Прочее clients_get/update, agencyclients_get/add/update/add_passport_organization/add_passport_organization_member, businesses_get, feeds_get/add/update/delete, leads_get, negativekeywordsharedsets_get/add/update/delete, keywordsresearch_has_search_volume, keywordsresearch_deduplicate, turbopages_get

Read the full file on GitHub · 217 lines

Files

What ships with it

1 file 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.

  1. 10d ago First seen · 217 lines · 55 tokens per session scan A aede60d52900

Subscribe to this mod's changes

yandex-direct is a skill published in the GitHub repository nikolaymokh-dev/yandex-direct-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 4,068 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to yandex-direct, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories