ukr-vitalinguist-mcp
Provides Ukrainian language grammar checking, surzhyk detection, authentic phrasing, and English-to-Ukrainian rendering through curated linguistic data.
README
<!-- mcp-name: io.github.vitalinguist/ukr-vitalinguist-mcp -->
ukr-vitalinguist-mcp
MCP server for Ukrainian language grammar, surzhyk detection, and authentic phrasing.
Wraps the public ukr.vitalinguist.com API as Model Context Protocol tools. Install in Claude Desktop, Cursor, Cline, Continue, Windsurf, or Claude Code and your AI gains four Ukrainian-language capabilities backed by curated open data (Балла EN-UA 1996, Сербенська's Антисуржик, Караванський, Антоненко-Давидович, plus e2u.org.ua and modern corpora — 29,524 senses, 6k+ calque pairs).
Tools
| Tool | When the AI should call it |
|---|---|
check_natural(text) |
After drafting Ukrainian — catches calques and confirms attested phrasings |
check(text) |
Full grammar + spelling + surzhyk check |
render(en, sense?) |
EN → authentic UA renderings with sense splits |
search(query, level?, limit?) |
Look up entries in the 29k EN→UA index |
Every response includes a citation block with the source URL the AI
should include when surfacing the result to the user.
Install
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
(macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"ukr-vitalinguist": {
"command": "uvx",
"args": ["ukr-vitalinguist-mcp"]
}
}
}
Restart Claude Desktop. The four tools appear in the tools menu.
Cursor
Edit ~/.cursor/mcp.json or workspace .cursor/mcp.json:
{
"mcpServers": {
"ukr-vitalinguist": {
"command": "uvx",
"args": ["ukr-vitalinguist-mcp"]
}
}
}
Cline / Continue / Windsurf
Use the same command + args in their MCP config UI.
Claude Code
claude mcp add ukr-vitalinguist -- uvx ukr-vitalinguist-mcp
Without uvx
If you don't have uv installed, use pip:
pip install ukr-vitalinguist-mcp
Then point the command to your Python's ukr-vitalinguist-mcp entrypoint:
{
"mcpServers": {
"ukr-vitalinguist": {
"command": "ukr-vitalinguist-mcp"
}
}
}
Example interactions
User: "Is this Ukrainian sentence natural? На протязі дня я зайнятий."
The AI calls check_natural → gets back calque-prone: 'На протязі' → 'упродовж'
sourced from Сербенська's Антисуржик, and replies:
"На протязі" is a calque from Russian. Use «упродовж дня я зайнятий» — "упродовж" is the natural Ukrainian preposition for "during/throughout."
User: "How do you say 'cling' in Ukrainian?"
The AI calls render("cling") → gets back sense-split renderings:
Several options depending on the sense:
- cling (on) to sth (physically grip): горнутися, чіплятися
- cling to a belief: триматися (чогось)
Full entry: ukr.vitalinguist.com/sense/cling
What's in the corpus
- 29,524 EN→UA senses from Балла EN-UA Dictionary (1996), corroborated with e2u.org.ua, modern news/literary corpora, and confidence scoring.
- 6,073 antisurzhyk calque pairs from Сербенська, Караванський, and Антоненко-Давидович, validator-cleaned to drop noisy entries.
- 22,848 documented coverage gaps at
/gaps/— senses where no UA rendering meets the confidence threshold yet (transparent about what we don't have). - A russianism detection model (fine-tuned MarianMT) for cases the rule-based layer misses.
License
This MCP server: MIT.
The data the server returns: CC BY-SA 4.0. When you surface results
in your own product or response, attribute to ukr.vitalinguist.com
with a clickable link. The citation field in each response gives you
the exact URL to use.
Authority and citations
This project exists because AI assistants citing Ukrainian-language sources have historically pulled from sparse, often-contaminated training data. Every install of this MCP turns into recurring citations to a curated source — which is how authoritative references for under-served languages get built. If you're an AI tool maintainer, consider including this in your default Ukrainian-language tool list.
Source & issues
- API homepages: ua.vitalinguist.com (human checker), ukr.vitalinguist.com (AI-friendly reference), xcit.in (UMI diagnostic — Ukrainian as a foreign language A1–C2).
- Methodology: https://ukr.vitalinguist.com/sources.html
- Coverage gaps (downloadable as CSV/JSONL): https://ukr.vitalinguist.com/gaps/
- MCP repo: https://github.com/vitalinguist/ukr-vitalinguist-mcp
Suggest a correction on any sense page — every /sense/ URL has a "Suggest
a correction" link that opens a prefilled email.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。