SergeyKrin9/mcp-servers

SergeyKrin9/mcp-servers

Russian-market marketing & ops MCP toolkit. 7 unified servers for Yandex.Direct, Yandex.Webmaster, Google Search Console (RU), YouTube Data API, VK Wall, Telegram publishing, and Click.ru (Telegram Ads + VK Ads + Yandex.Direct unified). The only complete RU-platform bundle for AI agents.

Category
访问服务器

README

<img src="https://capsule-render.vercel.app/api?type=waving&color=0:1a1a1d,50:c08a52,100:1a1a1d&height=200&section=header&text=MCP%20Servers&fontSize=52&fontColor=f5f1e8&fontAlignY=38&desc=Russian-market%20marketing%20%26%20ops%20toolkit%20for%20Claude%20%2F%20Cursor%20%2F%20Windsurf&descSize=14&descAlignY=62" alt="MCP Servers" />

<div align="center">

<p> <a href="https://github.com/SergeyKrin9/mcp-servers/stargazers"><img src="https://img.shields.io/github/stars/SergeyKrin9/mcp-servers?style=for-the-badge&color=c08a52&logo=github&labelColor=1a1a1d"></a> <a href="https://github.com/SergeyKrin9/mcp-servers/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-c08a52?style=for-the-badge&labelColor=1a1a1d"></a> <img src="https://img.shields.io/badge/Python-3.10%2B-c08a52?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a1d"> <img src="https://img.shields.io/badge/MCP-protocol-FF6B35?style=for-the-badge&logo=anthropic&logoColor=white&labelColor=1a1a1d"> </p>

<sub>🐍 Python · 🇷🇺 Russian market · 🎖️ The only unified RU-platform MCP bundle · 🤖 7 servers</sub>

</div>

[!IMPORTANT] The only unified MCP toolkit for Russian-market platforms. Yandex.Direct, Yandex.Webmaster, Yandex.Metrika (via energyboost), Google Search Console, YouTube, VK, Telegram, Click.ru. No equivalent exists in awesome-mcp-servers. If you do SEO/SMM/PPC for a Russian audience and use Claude — this is your missing kit.

A collection of 7 custom Model Context Protocol (MCP) servers that wire marketing platforms into LLM-agent loops. Built so an agent (Claude Code, Claude Desktop, Cursor, Windsurf) can run ad campaigns, read analytics, publish posts, and check SEO health directly — without humans clicking buttons.

If you don't know what MCP is, start here — it's Anthropic's open protocol for plugging tools into LLM apps.

What's inside

Server What it exposes to the agent
clickru/ Click.ru API — Telegram Ads, VK Ads, Yandex.Direct campaigns, balances, reports, bid manager
yadirect/ Yandex.Direct — create/pause campaigns, manage keywords, bids, ad copy
yandex-webmaster/ Yandex.Webmaster — indexing, top queries, sitemap, recrawl, problem detection
gsc/ Google Search Console — top queries, pages, country breakdown, indexed status
youtube/ YouTube Data API — videos, channels, comments, transcripts, trending
vk/ VK Wall API — publish, edit, pin posts, upload photos, stats
edaru-telegram/ Telegram Bot API — publish/edit/delete/pin posts in configured channels

Together they cover the full growth stack for a typical Russian-market product: paid ads (Direct + Telegram Ads + VK Ads via Click.ru), organic search (Yandex Webmaster + GSC), and content distribution (VK + Telegram).

Why this matters

In 2026 the bottleneck of growth isn't "what to do" — agents can plan. It's the glue between AI plans and platform APIs. These servers are that glue.

A typical workflow an LLM-agent can now run unattended:

  1. gsc.get_top_queries('edaru.su') → see which keywords are climbing
  2. yandex-webmaster.get_top_queries('edaru.su') → cross-check on Yandex
  3. yadirect.get_keywords('campaign_id=...') → see which keywords we already bid on
  4. Decide on new keywords to add → yadirect.add_negative_keywords(...), adjust bids
  5. vk.post_to_wall(...) and edaru-telegram.publish_post(...) to push fresh content
  6. Next day: clickru.get_campaign_stats(...) to see what worked

All without a marketer touching the console.

⚡ Quickstart (3 steps)

1. Clone & install:

git clone https://github.com/SergeyKrin9/mcp-servers.git
cd mcp-servers/yadirect            # or any other server
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt    # if present
cp .env.example .env               # fill in your credentials

2. Wire into your AI host:

<details> <summary><strong>Claude Desktop / Claude Code</strong> (<code>~/Library/Application Support/Claude/claude_desktop_config.json</code>)</summary>

{
  "mcpServers": {
    "yandex-direct": {
      "command": "/abs/path/to/mcp-servers/yadirect/.venv/bin/python3",
      "args": ["/abs/path/to/mcp-servers/yadirect/server.py"],
      "env": { "YANDEX_DIRECT_TOKEN": "your-token" }
    }
  }
}

</details>

<details> <summary><strong>Cursor</strong> (<code>~/.cursor/mcp.json</code>) — same JSON shape</summary>

{
  "mcpServers": {
    "vk": {
      "command": "/abs/path/to/.venv/bin/python3",
      "args": ["/abs/path/to/mcp-servers/vk/server.py"],
      "env": { "VK_TOKEN": "your-token", "VK_GROUP_ID": "123456" }
    }
  }
}

</details>

<details> <summary><strong>Windsurf</strong> (Settings → MCP Servers → Add) — same JSON shape</summary>

Identical config — Windsurf uses the same MCP server format. </details>

3. Test the loop. Open a fresh Claude chat and ask:

"Show me the top 5 search queries for edaru.su from Google Search Console for the last 7 days, then check the same in Yandex.Webmaster, then queue new keywords matching the gaps to my Yandex.Direct campaign."

If everything's wired right, Claude will run gsc.get_top_queries → yandex-webmaster.get_top_queries → yadirect.add_keywords in one tool loop — without you opening a single dashboard.

Credentials needed

Server What to get
clickru Click.ru API key + account ID (in the Click.ru dashboard)
yadirect Yandex.Direct OAuth token via oauth.yandex.ru
yandex-webmaster Same OAuth flow as Direct, with webmaster:hostinfo,webmaster:verify scopes
gsc Google service account JSON with Search Console access
youtube YouTube Data API v3 key (Google Cloud Console)
vk VK group access token (admin rights)
edaru-telegram Telegram bot token (BotFather) + chat ID

yandex-webmaster/oauth_helper.py includes a working OAuth flow if you want to grab tokens locally.

Tech stack

  • Python 3.10+ · stdlib + requests
  • mcp Python SDK
  • One process per platform — easy to enable/disable independently

Roadmap

  • Telegram Ads MCP (independent of Click.ru, native API)
  • Plausible / Yandex.Metrika real-time MCP (currently only reports)
  • One-shot CLI wrappers so you can call any of these without an MCP host

⭐ Star history

<a href="https://www.star-history.com/#SergeyKrin9/mcp-servers&Date"> <img src="https://api.star-history.com/svg?repos=SergeyKrin9/mcp-servers&type=Date" alt="Star History" /> </a>

📚 Related work

  • agnis-workflow — the methodology that uses these MCP servers as first-class tools
  • broker-reels — production application: AI text-to-video for real estate marketing
  • awesome-mcp-servers — the canonical MCP catalog (no Russian-market entries yet — PR welcome)

<div align="center">

Author: Sergey Krinitsyn · sergeykrin98@gmail.com · GitHub

<sub>If you ship to a Russian audience and use Claude — drop a ⭐. It tells me to keep adding servers.</sub>

</div>

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选