multilingual-dictionary-mcp
MCP de Diccionario Multilingüe
Un servidor MCP para consultas de diccionarios multilingües con relaciones de palabras — sinónimos, antónimos, hiperónimos, hipónimos, merónimos, traducciones, etimología, definiciones, rimas y más — que cubre todos los idiomas combinando tres APIs públicas gratuitas:
ConceptNet — red semántica multilingüe (más de 80 idiomas, relaciones de palabras: sinónimo, antónimo, IsA, PartOf, RelatedTo, DerivedFrom, etc.)
Wiktionary — definiciones, etimología y pronunciación en más de 4000 idiomas
Datamuse — utilidades solo para inglés (rimas, palabras que suenan igual, "significa algo como", patrones de ortografía, disparadores contextuales)
Sin claves de API. Sin datos empaquetados. Solo conéctalo a Claude (o cualquier cliente MCP) y pregúntale sobre palabras en cualquier idioma.
Instalación
Desde npm
npm install -g multilingual-dictionary-mcpDesde GitHub Packages
npm install -g @eyalm321/multilingual-dictionary-mcp --registry=https://npm.pkg.github.comConfiguración de Claude Desktop / Claude Code
{
"mcpServers": {
"multilingual-dictionary": {
"command": "npx",
"args": ["-y", "multilingual-dictionary-mcp"]
}
}
}Related MCP server: word-orb
Herramientas
Relaciones de palabras multilingües (ConceptNet)
Todas estas aceptan una word (palabra), un código de language (idioma) ISO 639-1 (por defecto es en) y un limit (límite). Funciona para inglés, español, francés, alemán, italiano, ruso, hebreo, árabe, latín, chino, japonés y más de 70 idiomas adicionales.
Herramienta | Descripción |
| Palabras con significado similar |
| Opuestos |
| Términos vagamente asociados (bordes RelatedTo) |
| Conceptos más amplios/padres (perro → mamífero) |
| Conceptos más estrechos/hijos (perro → caniche) |
| Partes/componentes (coche → rueda) |
| Todos que contienen esto (rueda → coche) |
| Raíces etimológicas |
| Cognados y raíces compartidas entre idiomas |
| Propósitos típicos (cuchillo → cortar) |
| Acciones típicas (perro → ladrar) |
| Ubicaciones típicas (libro → biblioteca) |
| Sinónimos interlingües — traduce una palabra |
| Todas las relaciones para una palabra en una sola llamada |
Definiciones y etimología (Wiktionary)
Herramienta | Descripción |
| Definiciones agrupadas por idioma (más de 4000 idiomas a través de en.wiktionary) |
| Breve resumen en texto plano de cualquier edición de Wiktionary |
| Sección de etimología, texto plano |
| Sección de pronunciación (típicamente IPA) |
| Busca en una edición de Wiktionary páginas coincidentes |
| Palabra aleatoria de cualquier edición de Wiktionary |
Utilidades específicas para inglés (Datamuse)
Herramienta | Descripción |
| Rimas perfectas o cercanas |
| Homófonos / palabras que suenan igual |
| "Significa aproximadamente" basado en ML — más amplio que los sinónimos |
| Patrón de ortografía con comodines |
| Autocompletar |
| Términos estadísticamente asociados (vaca → leche, granja) |
| Palabras que siguen comúnmente (beber → café) |
| Palabras que preceden comúnmente (audiencia → cautiva) |
Gestión de caché
Herramienta | Descripción |
| Inspeccionar aciertos/fallos/tamaño de la caché de respuestas en memoria |
| Forzar nuevas búsquedas ascendentes borrando la caché |
Caché
Cada respuesta ascendente exitosa se almacena en caché en memoria durante la vida útil del proceso del servidor, indexada por la URL completa de la solicitud. Las llamadas de seguimiento idénticas dentro de la misma sesión devuelven resultados al instante sin volver a consultar a ConceptNet/Wiktionary/Datamuse.
TTL predeterminado: 24 horas
Entradas máximas predeterminadas: 5000 (evicción LRU)
Deshabilitado para
dictionary_random(que se supone que varía)Sin persistencia en disco — la caché se reconstruye en cada inicio del servidor
Ajustar mediante variables de entorno:
MDM_DISABLE_CACHE=true # turn caching off
MDM_CACHE_TTL_MS=3600000 # 1 hour TTL
MDM_CACHE_MAX_ENTRIES=10000 # bigger cacheEjemplos
> What are the synonyms of "feliz" in Spanish?
[uses dictionary_synonyms with language: "es"]
> Translate "happiness" into Hebrew
[uses dictionary_translate with language: "en", targetLanguage: "he"]
> What's the etymology of the word "serendipity"?
[uses dictionary_etymology]
> Find me words that rhyme with "orange"
[uses dictionary_rhymes]
> What are the parts of a bicycle?
[uses dictionary_meronyms with word: "bicycle"]Desarrollo
npm install
npm run build # TypeScript compile
npm test # vitest run
npm run test:watch # vitest watch
npm run dev # ts-node entry pointDiseño del proyecto
src/
├── index.ts # MCP server entry
├── client.ts # HTTP wrappers for ConceptNet / Wiktionary / Datamuse
├── tools/
│ ├── relations.ts # ConceptNet-backed multilingual relation tools
│ ├── definitions.ts # Wiktionary-backed definition/etymology tools
│ └── english.ts # Datamuse-backed English utilities
└── __tests__/ # vitest specsCI / Lanzamiento
CI se ejecuta en cada push y PR contra
main, en Node 20 y 22.Publicar se ejecuta cuando se publica un GitHub Release — prueba, construye y luego publica en ambos npm (como
multilingual-dictionary-mcp) y GitHub Packages (como@eyalm321/multilingual-dictionary-mcp).
Para realizar un lanzamiento:
Aumenta la
versionenpackage.jsony confirma los cambios.Etiqueta y envía (ej.
git tag v0.1.1 && git push --tags).Crea un GitHub Release apuntando a la etiqueta — el flujo de trabajo de publicación se encarga del resto.
El flujo de trabajo de publicación espera dos secretos del repositorio: NPM_TOKEN (token de automatización de npm) y GITHUB_TOKEN (proporcionado automáticamente por GitHub Actions).
Licencia
MIT © Eyalm321
Available Tools
28 toolsdictionary_all_relationsC
All edges (every relation type) for a word in one call from offline ConceptNet.
Inputs: word (required), language, limit.
dictionary_antonymsB
Get antonyms (opposites) for a word in any language using offline ConceptNet.
Inputs: word (required), language, limit.
dictionary_at_locationB
Typical locations (AtLocation) via offline ConceptNet. E.g. book -> library.
Inputs: word (required), language, limit.
dictionary_capable_ofB
Typical actions (CapableOf) via offline ConceptNet. E.g. dog -> bark.
Inputs: word (required), language, limit.
dictionary_derived_fromC
Derivation relations via offline ConceptNet DerivedFrom.
Inputs: word (required), language, limit.
dictionary_etymologyA
Return etymology text for a word from the offline Wiktextract corpus.
Inputs: word (required), language.
dictionary_holonymsB
Holonyms (wholes that contain this word) via offline ConceptNet reverse PartOf.
Inputs: word (required), language, limit.
dictionary_hypernymsA
Hypernyms (broader concepts) via offline ConceptNet IsA. E.g. dog -> mammal.
Inputs: word (required), language, limit.
dictionary_hyponymsB
Hyponyms (narrower concepts) via offline ConceptNet IsA. E.g. dog -> poodle.
Inputs: word (required), language, limit.
dictionary_installA
Manually kick off (or re-trigger) the offline data download. Returns immediately while the install runs in the background. Idempotent — calling repeatedly while a download is in progress is a no-op. Use dictionary_status to track progress.
Inputs: no named parameters.
dictionary_lookupA
Look up definitions for a word from the offline Wiktextract corpus (4,755 languages, 10.5M entries). Returns part-of-speech, definitions per sense, IPA, etymology, and translations grouped by language.
Inputs: word (required), language, limit.
dictionary_means_likeA
Find words/phrases meaning approximately the same as the input via offline Numberbatch embedding cosine. Multilingual — works in any of the 78 languages Numberbatch covers.
Inputs: query (required), language, limit.
dictionary_meronymsC
Meronyms (parts/components) via offline ConceptNet PartOf. E.g. car -> wheel.
Inputs: word (required), language, limit.
dictionary_pronunciationB
Return IPA pronunciation(s) for a word from the offline Wiktextract corpus.
Inputs: word (required), language.
dictionary_randomA
Return a random word entry from the offline Wiktextract corpus, optionally filtered to a language.
Inputs: language.
dictionary_rhymesA
Find words that rhyme with the input word. English only — backed by the offline CMU Pronouncing Dictionary.
Inputs: word (required), limit, perfect.
dictionary_searchA
Prefix-search the offline Wiktextract corpus for words matching a query. Useful when you don't know the exact spelling.
Inputs: query (required), language, limit.
dictionary_semantic_neighborsA
Embedding-based nearest neighbors via Numberbatch. Returns words from the same OR a different language, sorted by cosine similarity. Multilingual (78 languages).
Inputs: word (required), language, targetLanguage, limit.
dictionary_sounds_likeB
Find English words that sound similar to the input (homophones / soundalikes) via offline CMU dict.
Inputs: word (required), limit.
dictionary_spelled_likeA
Find English words matching a spelling pattern via offline CMU dict. '?' = any single letter, '*' = any zero+ letters. Useful for crosswords.
Inputs: pattern (required), limit.
dictionary_statusA
Get the current state of the offline data installation. Always available — even before the bundle has finished downloading. Returns: state (pending/downloading/ready/failed), per-artifact progress, total bytes downloaded, data directory, CDN URL, manifest version, and any error.
Inputs: no named parameters.
dictionary_suggestA
Get autocomplete suggestions for a partial English word via offline CMU dict (shortest matches first).
Inputs: prefix (required), limit.
dictionary_summaryA
Get a brief plain-text summary of a word's senses from the offline Wiktextract data. Concatenates the first definition of each sense.
Inputs: word (required), language.
dictionary_synonymsA
Get synonyms for a word in any language using the offline ConceptNet 5.7 SQLite (24M edges, 80+ languages).
Inputs: word (required), language, limit.
dictionary_translateC
Translate a word to another language via offline ConceptNet's cross-lingual Synonym links. Returns the same concept expressed in different languages.
Inputs: word (required), language, targetLanguage, limit.
dictionary_used_forB
Typical uses (UsedFor) via offline ConceptNet. E.g. knife -> cutting.
Inputs: word (required), language, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 28 tools
Each tool targets a specific linguistic relation or operation with clear, distinct descriptions. Even potentially overlapping tools like synonyms, means_like, and related are differentiated by their underlying data sources (ConceptNet vs Numberbatch embeddings).
All tools follow a consistent 'dictionary_' prefix followed by a descriptive snake_case name. The pattern is uniform with no mixing of conventions or styles.
28 tools is on the higher end but justified by the comprehensive coverage of dictionary features (definitions, etymology, pronunciation, semantic relations, search, data management). It remains manageable and focused.
The tool surface covers a wide range of dictionary and lexical relations: definitions, pronunciations, etymology, synonyms, antonyms, hypernyms, hyponyms, meronyms, holonyms, translations, rhymes, spelling, autocomplete, random access, and data installation status. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
MCP server for Chinese dictionary lookup: character definitions, pinyin, stroke order and word
Wiktionary MCP — multilingual dictionary via Wikimedia REST + MediaWiki Action API
Dictionary MCP — wraps Free Dictionary API (free, no auth)
MCP server for Chinese idioms (chengyu): lookup by word, pinyin or meaning with explanation and
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that provides access to the Similar Words API, allowing users to search for and retrieve semantically related words. It enables language-based applications to query word similarities and relationships through a standardized interface.1MIT
- AlicenseNot gradedqualityCmaintenanceVocabulary intelligence MCP server — 162K words, 47 languages, definitions, IPA pronunciation, etymology, translations, and daily lessons. 19 tools for AI agents.2 npm1MIT
- AlicenseAqualityDmaintenanceMCP server for the Datamuse API that enables word finding like synonyms, rhymes, autocomplete, and more.1049 npm3MIT
- FlicenseNot gradedqualityDmaintenanceRemote MCP server for word definitions and random word retrieval via Oxford Dictionaries API, deployable on Vercel with bearer token authentication.-