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.
npx skills add axisrow/yandex-direct-mcp-plugin --skill yandex-directgit clone --depth 1 https://github.com/axisrow/yandex-direct-mcp-pluginWrote 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.
[](https://agentmods.dev/skills/axisrow/yandex-direct-mcp-plugin/yandex-direct)<a href="https://agentmods.dev/skills/axisrow/yandex-direct-mcp-plugin/yandex-direct"><img src="https://agentmods.dev/badge/skills/axisrow/yandex-direct-mcp-plugin/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.
<a href="https://agentmods.dev/skills/axisrow/yandex-direct-mcp-plugin/yandex-direct"><img src="https://agentmods.dev/badge/skills/axisrow/yandex-direct-mcp-plugin/yandex-direct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00055 | $0.04473 |
| Opus 5 | $0.00028 | $0.02237 |
| Sonnet 5 | $0.00011 | $0.00895 |
| Haiku 4.5 | $0.00006 | $0.00447 |
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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- yandex-direct — 97% identical, 28 lines differ
How it starts
The opening of the file, as written. The whole thing — 239 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:
- Вызови
auth_login()— он покажет ссылку для авторизации и запросит код через форму - Пользователю не нужно ничего знать заранее — flow полностью интерактивный
- 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 (149 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_campaignschanges_check_dictionarieskeywordsresearch_has_search_volumebids_set_autokeywordbids_set_autoaudiencetargets_set_bidsdynamicads_set_bidssmartadtargets_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/suspend/resume, 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 |
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.
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.
- 9d ago First seen · 239 lines · 55 tokens per session scan A 3ec2e201c6a0
yandex-direct is a skill published in the GitHub repository axisrow/yandex-direct-mcp-plugin (12 stars, last pushed 8d ago), licensed MIT. It adds 55 tokens to every session and 4,473 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…