ukr-vitalinguist-mcp

ukr-vitalinguist-mcp

Provides Ukrainian language grammar checking, surzhyk detection, authentic phrasing, and English-to-Ukrainian rendering through curated linguistic data.

Category
Visit Server

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."

Source: Сербенська, Антисуржик via ukr.vitalinguist.com


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

Suggest a correction on any sense page — every /sense/ URL has a "Suggest a correction" link that opens a prefilled email.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured