convez.ai
MCP ServerUtilidadesAvançado
Leo-Martin-Pala

Võro MCP Server

Leo-Martin-Pala/voro-mcp

Dicionário, corpus e análise linguística para Võro via MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que equipa modelos de linguagem com ferramentas práticas para a língua Võro: dicionário local, busca em corpus, análise morfológica, verificação ortográfica e gramatical. Melhora significativamente a capacidade de modelos de IA compreender, gerar, corrigir e traduzir textos em Võro, uma língua de recursos limitados.

Instalação

$npx convez-ai Leo-Martin-Pala/voro-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 4 meses
Versão
data-v1
Issues abertas
0
Contribuidores
2

Casos de uso

  • Tradução de textos para Võro com verificação de qualidade
  • Análise morfológica e geração de formas verbais em Võro
  • Suporte a falantes e aprendizes de Võro com correção automática

Veredito

Ferramenta especializada e bem-estruturada para um caso de uso específico (suporte ao Võro). Implementação técnica sólida com integração clara ao MCP, mas público restrito a comunidades de falantes de Võro e pesquisadores de linguística computacional.

README

A tradução para o português deste README ainda está na fila.

An MCP server for working with the Võro language: local dictionary and corpus lookup, GiellaLT-backed analysis/spellcheck/grammar tools, and Neurotõlge translation.

What it's for

This MCP server gives language models practical tools for working with the Võro language. Võro is a lower-resource language, so general-purpose language models may make more mistakes with it than with widely supported languages such as English, or even Estonian.

By connecting the model to dictionaries, corpus search, morphological analysis, spellchecking, grammar checking, translation, and form generation, this server helps improve the model’s ability to understand, generate, correct, and translate Võro text.

It can be useful for tasks such as Võro translation, checking and improving generated text, exploring real usage examples, generating word forms, detecting unknown words, and supporting people who are learning or working with the Võro language.

Install

Quick setup

On Debian/Ubuntu, one command does the whole setup.

make setup        # scripts/run_local_ubuntu.sh; see `make help` for every task

You need make, Python, and the usual shell tools installed first. The setup target installs the HFST/Divvun system binaries (adding the Apertium package repo first if your system can't already find divvun-gramcheck), downloads the SQLite datasets and the prebuilt Giella models, creates .venv, and installs the package. Smoke-test it with make test.

make test runs straight from the checkout (no install needed). Tests that need the SQLite datasets or the Giella tools skip with a hint when those aren't present, so a bare clone still reports green — run make data and make giella (or the full make setup) to actually exercise them.

  1. System binaries the Giella tools shell out to: hfst-optimized-lookup, hfst-ospell, cg3, divvun-checker. On Debian/Ubuntu they come from the Apertium nightly apt repo:

    curl -fsSL https://apertium.projectjj.com/apt/install-nightly.sh | sudo bash
    sudo apt-get install -y hfst hfst-ospell cg3 divvun-gramcheck perl gawk bash
    
  2. The package, into a virtualenv (make install):

    python3 -m venv .venv
    . .venv/bin/activate
    pip install -e .
    
  3. Data and models, they are pulled from GitHub releases:

    scripts/fetch_data.sh
    scripts/fetch_giella.sh
    
  4. Verify the external tools resolved (prints JSON and exits):

    vro-mcp-check
    

From least to most system-wide. Do the steps that apply, from the repo root.

  1. Client registration — unregister the server from whichever MCP client you added it to:

    claude mcp remove vro    # Claude Code
    codex mcp remove vro     # Codex CLI
    
  2. Local install — delete the virtualenv:

    rm -rf .venv
    
  3. Downloads — the SQLite datasets and Giella models (large; re-fetchable with make data / make giella):

    rm -rf data                 # SQLite datasets + the data/giella-share models
    rm -rf .cache/giella-build  # only if you built Giella from source
    rm -f .env                  # only if you created one for deployment
    

    To drop the code too, delete the directory you cloned into.

  4. The Apertium/Divvun apt repo — only if make setup added it (it skips this when divvun-gramcheck was already installable). Find the source it dropped and remove it:

    ls /etc/apt/sources.list.d/ | grep -i apertium
    sudo rm -f /etc/apt/sources.list.d/apertium*.list
    sudo apt-get update
    
  5. System packages — remove only the Võro-specific binaries. Leave shared tools (python3, git, make, perl, gawk, …) in place, since other software may depend on them:

    sudo apt-get remove hfst hfst-ospell cg3 divvun-gramcheck
    sudo apt-get autoremove        # optional: drop now-unused dependencies
    

Tools

ToolWhat it does
lookup_wordDictionary lookup (en↔vro).
find_usage_examplesFull-text corpus search for real usage.
word_exists_in_bagFast check whether a word form has been seen.
find_unknown_wordsList word forms in a text absent from the word bag.
find_unrecognized_wordsList text word forms that the GiellaLT analyzer returns as +?, with optional word-bag prefiltering.
analyze_wordGiellaLT morphological analysis.
generate_formsGiellaLT generation for one exact lemma + tag analysis.
spellcheck_vroToken-level spellcheck with suggestions.
grammar_check_vroSentence-level grammar check.
find_estonian_leakageScan a larger text and return a slim, deduped list of word forms (and phrases) with Estonian-looking endings.
lint_estonian_leakageIn-depth check of specific words/phrases: rule IDs, severities, messages, and hints.
suggest_correctionAnalyzer-verified fixes for a bad/unknown form.
translate_vroNeurotõlge/TartuNLP translation.
check_setupReport database and external Giella tool availability.

Most lookup tools accept a single word or a list for batched queries.

The open dictionary currently covers English↔Võro only.

Resources

Markdown references are exposed over MCP:

  • vro://grammar/noun-cases: noun/adjective/numeral/pronoun declension.
  • vro://grammar/verb-conjugation: verb conjugation, moods, tenses, voice.
  • vro://grammar/orthography-and-standard: writing system (alphabet, glottal stop q, palatalization, high õ, length and negation spelling) and Võro Institute standard-language orientation.
  • vro://guide/translator-prompt: translator/post-editor prompt and workflow for producing Võro text with these tools.

Configuration

The data lives under data/ and is fetched for you. make setup (or make data + make giella) downloads everything, so you normally configure nothing. The fetch scripts honour VRO_DATA_REPO, VRO_DATA_TAG, and VRO_GIELLA_TAG to point at a different release.

All path defaults are repo-local; override any with environment variables or a local .env where the deploy script supports it.

VariableDefaultDescription
VRO_DICTIONARY_DB./data/vro_dictionary.sqliteDictionary SQLite path used by lookup_word and correction suggestions.
VRO_CORPUS_DB./data/vro_corpus.sqliteCorpus SQLite path used by find_usage_examples.
VRO_WORD_BAG_DB./data/vro_word_bag.sqliteWord-bag SQLite path used by seen/unknown word checks.
VRO_NEUROTOLGE_BASE_URLhttps://api.tartunlp.ai/translation/v2Neurotõlge/TartuNLP translation API base URL.
VRO_ANALYZER_CMD./tools/giella/bin/analyze-vroCommand used for GiellaLT morphological analysis.
VRO_GENERATOR_CMD./tools/giella/bin/generate-vroCommand used for one-analysis GiellaLT form generation.
VRO_SPELLER_CMD./tools/giella/bin/spellcheck-vroCommand used for token spellchecking.
VRO_GRAMMAR_CMD./tools/giella/bin/grammar-check-vroCommand used for sentence grammar checking.
VRO_ANALYZER_MODEL./data/giella-share/giella/vro/analyser-gt-desc.hfstolModel path used by tools/giella/bin/analyze-vro.
VRO_GENERATOR_MODEL./data/giella-share/giella/vro/generator-gt-norm.hfstolModel path used by tools/giella/bin/generate-vro.
VRO_SPELLER_MODEL./data/giella-share/voikko/3/vro.zhfstSpeller archive path used by tools/giella/bin/spellcheck-vro.
VRO_GRAMMAR_MODEL./data/giella-share/voikko/4/vro.zcheckGrammar checker archive path used by tools/giella/bin/grammar-check-vro.
VRO_SPELLER_MAX_SUGGESTIONS10Maximum spelling suggestions returned per unknown token.
VRO_DATA_REPOLeo-Martin-Pala/voro-mcpGitHub repository used for dataset and Giella release downloads.
VRO_DATA_TAGdata-v1GitHub release tag fetched for vro-data.tar.xz by scripts/fetch_data.sh and Modal release hydration.
VRO_GIELLA_TAGgiella-v1GitHub release tag fetched for giella-share.tar.xz by scripts/fetch_giella.sh and Modal release hydration.
VRO_GIELLA_BUILD_DIR./.cache/giella-buildTemporary build directory for make giella-build.
VRO_GIELLA_ARTIFACT_DIR./data/giella-shareOutput directory for locally built Giella artifacts.
MCP_PATH/mcp locally; generated in .env for Modal deploysSecret hosted HTTP path segment for Modal; local stdio clients do not need it.
DATA_SOURCEreleaseModal deploy data source: release, local, or none.
FORCE_DATA0Set to 1 to overwrite existing Modal Volume data.
DATA_DIR./dataLocal data directory used when DATA_SOURCE=local.
NEW_SECRET0Set to 1 to rotate MCP_PATH during deploy and save it to .env.
LOCAL_SECRET0Set to 1 to push the MCP_PATH from .env/environment as-is and fail if it is empty (used by make deploy-local-secret).
MODAL_APP_NAMEvro-mcpModal app name used by deploy/undeploy scripts.
MODAL_VOLUME_NAMEvro-dataModal Volume name for SQLite data and Giella artifacts.
MODAL_SECRET_NAMEvro-mcp-secretModal secret name storing MCP_PATH.

Connect a client

All a client needs is the binary's absolute path. Run make local-url to print that path and ready-to-paste config for Claude Code and Codex.

Claude Code:

claude mcp add vro -- /absolute/path/to/vro-mcp-server/.venv/bin/vro-mcp-server

Codex:

codex mcp add vro -- /absolute/path/to/vro-mcp-server/.venv/bin/vro-mcp-server

Generic JSON MCP client configuration:

{
  "mcpServers": {
    "vro": {
      "command": "/absolute/path/to/vro-mcp-server/.venv/bin/vro-mcp-server",
      "cwd": "/absolute/path/to/vro-mcp-server"
    }
  }
}

Deployment

The local setup above runs the server on your own machine. To use it from anywhere — including the Claude and ChatGPT web apps — deploy it to Modal instead.

make deploy

This builds the server in Modal's cloud and prints a hosted HTTPS endpoint like:

https://<workspace>--vro-mcp-serve.modal.run/<secret>/mcp

Paste that URL into any MCP client (Claude Code, Codex, Claude web, ChatGPT) and you can reach the tools from anywhere, no local install needed. The server wakes on demand and sits idle for free between requests. The URL embeds a random secret path that acts as its password, so keep it private.

See DEPLOY.md for prerequisites, connecting each client, and the full set of deploy commands.

License

Code is MIT (LICENSE). The SQLite datasets are CC-BY-SA-4.0 and the prebuilt GiellaLT models are GPL-3.0. Both are distributed as separate release assets, each bundling its own license and attribution. See NOTICE.md for scope and source summaries.

Ver o original no GitHub

Bom para

Relacionados