What is keyword-research-ru?

A keyword-research tool for Yandex, the search engine widely used in Russia and nearby markets. It measures search demand, seasonality, regional interest, and related phrases.

Use it to estimate search volume, compare demand by region and season, expand keyword lists through suggestions, and inspect related Wordstat results.

It helps avoid inflated demand estimates by separating exact searches from broader matches and supports larger keyword lists when quotas are a problem.

keyword-research-ru — Skill for Claude Code by antohins

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 antohins/seo-tools-mcp --skill keyword-research-ru

Clone the repo

git clone --depth 1 https://github.com/antohins/seo-tools-mcp

Made for: Claude Code.

Or install seo-tools, the plugin that ships this one along with the rest of its 1 skill.

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/antohins/seo-tools-mcp/keyword-research-ru/github.svg)](https://agentmods.dev/skills/antohins/seo-tools-mcp/keyword-research-ru)

Your own site

<a href="https://agentmods.dev/skills/antohins/seo-tools-mcp/keyword-research-ru"><img src="https://agentmods.dev/badge/skills/antohins/seo-tools-mcp/keyword-research-ru/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/antohins/seo-tools-mcp/keyword-research-ru"><img src="https://agentmods.dev/badge/skills/antohins/seo-tools-mcp/keyword-research-ru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,204 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	$0.00081	$0.01204
Opus 5	$0.00041	$0.00602
Sonnet 5	$0.00016	$0.00241
Haiku 4.5	$0.00008	$0.00120

Measured 12d ago against content hash a0571b9650aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

keyword-research-ru 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 12d 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.

plugins/seo-tools/skills/keyword-research-ru/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Семантика под Яндекс: частотности и спрос

Два источника, между ними надо выбрать

wordstat — официальный Wordstat API v2 через Yandex Cloud. Бесплатный, но с квотами: 10 запросов в секунду и 100 запросов в час. Точные цифры, доступ ко всем типам разреза.
xmlstock_wordstat* — те же данные через XMLStock. Платно (~19 ₽/1000, дороже обычной выдачи), зато без часовой квоты.

Правило: по умолчанию wordstat. Переключаться на xmlstock_wordstat только когда пул больше сотни фраз и часовая квота становится узким местом — и предупредить пользователя, что это уже платно.

Операторы: без них цифра врёт

wordstat_frequency сразу возвращает оба числа:

freq_broad — широкая частотность. Включает все словоформы, любой порядок и всё, что содержит фразу. Для «купить телефон» сюда попадёт «купить телефон в кредит бу недорого».
freq_exact — точная ("!слово !слово"): ровно эта фраза, ровно в этих формах.

Планировать трафик по freq_broad — классическая ошибка: она завышает в разы. Для оценки брать freq_exact, широкую — только чтобы понять размер темы целиком.

Остальные операторы (в query): "…" фиксирует состав, ! — форму слова, + возвращает стоп-слово, - минусует, [ ] фиксирует порядок.

Расширение пула

wordstat_frequency за один вызов даёт обе колонки Вордстата:

related — левая колонка, уточняющие запросы (то, что ищут вместе с фразой);
associations — правая колонка, похожие запросы (≤20, точка входа в соседние темы).

related_truncated: true означает, что список обрезан по relatedLimit — за оставшимся надо идти отдельным вызовом с бо́льшим лимитом.

Ещё расширение: xmlriver_suggest — подсказки Google, до 50 фраз за вызов, но платно за каждую фразу (50 фраз = 50 списаний).

Сезонность

wordstat_dynamics — и здесь спрятана ловушка, из-за которой запрос молча вернёт не то:

операторы (!, кавычки) работают только при period: daily;
monthly требует fromDate = 1-е число и toDate = последний день месяца;
weekly требует fromDate = понедельник;
глубина: weekly/monthly — с 2018 года, daily — только последние 60 дней.

Read the full file on GitHub · 85 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.

12d ago First seen · 85 lines · 81 tokens per session scan A a0571b9650aa

Subscribe to this mod's changes

keyword-research-ru is a skill published in the GitHub repository antohins/seo-tools-mcp (3 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,204 once invoked, about $0.0004 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 2026-08-31.

Marketing and SEO claude mcp model-context-protocol search-console seo yandex

yandex-webmaster

Loaded automatically when the description matches the active task. Read only the section you need, then follow the link to the relevant reference file.

VKirill/claude-lane-stack · 180 tokens

mutagen

Skill "mutagen" from VKirill/claude-lane-stack, covering 🎯 version requirements (august 2026), usage, use this skill when, do not use this skill when and purpose.

VKirill/claude-lane-stack · 262 tokens

xmlstock

Skill "xmlstock" from VKirill/claude-lane-stack, covering 🎯 version requirements (august 2026), usage, use this skill when, do not use this skill when and purpose.

VKirill/claude-lane-stack · 383 tokens

google-search-console

Skill "google-search-console" from VKirill/claude-lane-stack, covering version requirements (may 2026), usage, use this skill when, do not use this skill when and purpose.

VKirill/claude-lane-stack · 172 tokens

marketing-skills

42 marketing agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more coding agents. 7 pods: content, SEO, CRO, channels, growth, intelligence, sales. Foundation context + orchestration router. 27 Python tools (stdlib-only).

h3rb3rn/moe-sovereign · 66 tokens

yandex-workspace

Guide for agents using the Yandex Workspace MCP server.

denis-samatov/yandex-workspace-mcp · 15 tokens