latin
Grounds LLMs in real Latin: Wiktionary lemmas, Morpheus inflections, citations.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"latin": {
"url": "https://latin.valksor.com/mcp"
}
}
}リモートエンドポイント
https://latin.valksor.com/mcpstreamable-httpできること
ツール一覧
ツール(3)
🟢latin_search(query, search_language, include_forms, max_forms)
Look a Latin word up on Wiktionary and return its senses plus full declension/conjugation tables — attested content, not invented. Any form of the word works; an inflected query is resolved to its lemma automatically (via previously cached paradigms or the Morpheus analyzer) and the result notes the resolution. With search_language='eng' the query is an English word instead: the result lists its per-sense Latin equivalents (the translations block) plus their expanded entries. Returns Markdown plus the same result as structuredContent matching the declared outputSchema. Results are cached server-side; first-time queries reach the live upstream politely and calls are rate limited — on a rate-limit error, wait a few seconds and retry. Content is from en.wiktionary.org (CC BY-SA 4.0 — attribute and share alike if republished).
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"description": "The word to look up, in the language search_language names. Latin (default): a SINGLE word, any form — an inflected form ('amavit') is resolved to its lemma ('amo') automatically, and the result names it (search_method tells you how; resolved_lemma is the lemma to follow for the full paradigm); macrons are optional ('amo' and 'amō' both work). English (search_language='eng'): the English word whose Latin equivalents you want — multiword entries like 'give up' work.",
"maxLength": 80,
"minLength": 1,
"title": "Query",
"type": "string"
},
"search_language": {
"$ref": "#/$defs/SearchLanguage",
"default": "lat",
"description": "Language the query word is in: 'lat' (default) looks the Latin word up directly; 'eng' finds the Latin equivalents of an English word (per-sense, from Wiktionary's translation tables) and returns their full entries. Glosses are in English either way."
},
"include_forms": {
"default": true,
"description": "When true (default), each match's full declension/conjugation table is returned INLINE — usable cases/tenses in ONE call, no follow-up latin_get_inflections. Set false for a cheap screen of which entries exist. Bounded by a per-search cap — use max_forms to adjust per call. For eng queries this governs the expanded Latin entries; the per-sense translations list itself is always returned.",
"title": "Include Forms",
"type": "boolean"
},
"max_forms": {
"anyOf": [
{
"maximum": 12,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional override for how many inflection tables to expand this call (0–12). On an uncached query each table is one politely paced upstream fetch, so high values on cold queries are slow. Omit for the server default.",
"title": "Max Forms"
}
},
"required": [
"query"
],
"$defs": {
"SearchLanguage": {
"description": "The query language. ``lat`` looks a Latin word up directly (any of its forms —\nan inflected query resolves via the form index or Morpheus). ``eng`` searches in\nreverse: the English Wiktionary page for the query word lists per-sense Latin\ntranslations, and each distinct Latin lemma is then looked up normally.",
"enum": [
"lat",
"eng"
],
"title": "SearchLanguage",
"type": "string"
}
},
"title": "latin_searchArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"language": {
"$ref": "#/$defs/SearchLanguage"
},
"found": {
"description": "False when nothing matched. For an eng query, True means Latin translations were found — entries may still be empty when none of them could be expanded (see translations).",
"title": "Found",
"type": "boolean"
},
"handles": {
"items": {
"$ref": "#/$defs/InflectionHandle"
},
"title": "Handles",
"type": "array"
},
"entries": {
"items": {
"$ref": "#/$defs/Entry"
},
"title": "Entries",
"type": "array"
},
"forms_truncated": {
"default": 0,
"description": "How many handles did NOT get an inline table because the per-search cap was reached.",
"title": "Forms Truncated",
"type": "integer"
},
"translations": {
"description": "Populated only for eng queries (always [] for lat): the Latin terms each English sense translates to, in sense order. Entries/handles below are the expanded dictionary entries of those terms.",
"items": {
"$ref": "#/$defs/TranslationSense"
},
"title": "Translations",
"type": "array"
},
"translations_truncated": {
"default": 0,
"description": "How many distinct translated lemmas were NOT expanded into entries because the per-search expansion cap was reached (they still appear under translations).",
"title": "Translations Truncated",
"type": "integer"
},
"search_method": {
"default": "direct",
"description": "How the match was found: 'direct' = the query itself matched; 'lemma_index' = an inflected form resolved via a previously cached paradigm; 'morpheus' = resolved via the Morpheus morphological analyzer; 'translations' = an English query resolved via Wiktionary translation tables.",
"enum": [
"direct",
"lemma_index",
"morpheus",
"translations"
],
"title": "Search Method",
"type": "string"
},
"resolved_from": {
"default": "",
"description": "The query whose lemma this result names (paired with resolved_lemma); else empty. lat queries only (always empty for eng). Set both when an inflected miss was re-searched (search_method lemma_index/morpheus) and when the query's own page is a form-of stub returned directly (search_method stays 'direct').",
"title": "Resolved From",
"type": "string"
},
"resolved_lemma": {
"default": "",
"description": "The lemma this query maps to; else empty. lat queries only. With search_method 'lemma_index'/'morpheus' the entries below ARE this lemma's; with 'direct' the entries are the queried form-of stub and this names the lemma whose page holds the full paradigm (search it / latin_get_inflections it). Only set when unambiguous — a form mapping to several lemmas leaves it empty (use lemmatize); the per-sense form_of still carries each.",
"title": "Resolved Lemma",
"type": "string"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"query",
"language",
"found"
],
"$defs": {
"Entry": {
"description": "One Latin entry on the page: the headword (page title) with one\npart-of-speech section's senses.",
"properties": {
"headword": {
"title": "Headword",
"type": "string"
},
"part_of_speech": {
"default": "",
"title": "Part Of Speech",
"type": "string"
},
"entry_id": {
"default": "",
"description": "Page title — feed to latin_get_inflections.",
"title": "Entry Id",
"type": "string"
},
"word_class": {
"default": "",
"description": "POS section — feed to latin_get_inflections.",
"title": "Word Class",
"type": "string"
},
"senses": {
"items": {
"$ref": "#/$defs/Sense"
},
"title": "Senses",
"type": "array"
}
},
"required": [
"headword"
],
"title": "Entry",
"type": "object"
},
"InflectionHandle": {
"description": "A structured anchor for fetching a full paradigm: feed ``entry_id`` (the page\ntitle) + ``word_class`` (the POS section) to ``latin_get_inflections`` — or ask\n``search`` to include the table inline (``forms``).",
"properties": {
"entry_id": {
"description": "Wiktionary page title — the lemma itself.",
"title": "Entry Id",
"type": "string"
},
"word_class": {
"description": "Part-of-speech section, e.g. 'verb', 'noun'.",
"title": "Word Class",
"type": "string"
},
"context": {
"default": "",
"description": "Nearby headword / hint.",
"title": "Context",
"type": "string"
},
"pos_hint": {
"default": "",
"description": "Part-of-speech hint.",
"title": "Pos Hint",
"type": "string"
},
"forms": {
"anyOf": [
{
"discriminator": {
"mapping": {
"nominal": "#/$defs/LatinNominalParadigm",
"not_found": "#/$defs/ParadigmNotFound",
"verbal": "#/$defs/LatinVerbalParadigm"
},
"propertyName": "category"
},
"oneOf": [
{
"$ref": "#/$defs/LatinNominalParadigm"
},
{
"$ref": "#/$defs/LatinVerbalParadigm"
},
{
"$ref": "#/$defs/ParadigmNotFound"
}
]
},
{
"type": "null"
}
],
"default": null,
"description": "The full paradigm, populated when a search is asked to include forms. None when not requested or beyond the cap.",
"title": "Forms"
}
},
"required": [
"entry_id",
"word_class"
],
"title": "InflectionHandle",
"type": "object"
},
"LatinNominalParadigm": {
"description": "Declension of a noun/adjective/etc.: case → {singular, plural}.\n\n``category`` discriminates this from the verbal and not-found shapes — switch on\nit before reading the body.",
"properties": {
"category": {
"const": "nominal",
"default": "nominal",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": true,
"default": true,
"title": "Found",
"type": "boolean"
},
"cases": {
"additionalProperties": {
"$ref": "#/$defs/NumberForms"
},
"description": "Case name (lower-case: 'nominative', 'genitive', …) → its singular/plural forms, in table order.",
"title": "Cases",
"type": "object"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class",
"cases"
],
"title": "LatinNominalParadigm",
"type": "object"
},
"LatinVerbalParadigm": {
"description": "Conjugation of a verb, grouped the way Wiktionary's table is:\nfinite cells keyed by \"<voice> <mood> <tense>\" → person/number → form, plus the\nnon-finite sections (infinitives, participles, gerund, supine).",
"properties": {
"category": {
"const": "verbal",
"default": "verbal",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": true,
"default": true,
"title": "Found",
"type": "boolean"
},
"finite": {
"additionalProperties": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"description": "'<voice> <mood> <tense>' (lower-case, e.g. 'active indicative present') → person/number ('first singular' … 'third plural') → the form. Periphrastic rows (e.g. passive perfect) appear under the single key 'all'. Alternates are comma-separated; an em-dash cell (no such form) is omitted.",
"title": "Finite",
"type": "object"
},
"nonfinite": {
"additionalProperties": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"description": "Non-finite section ('infinitive', 'participle', 'gerund', 'supine') → label ('active present', 'genitive', …) → the form.",
"title": "Nonfinite",
"type": "object"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class",
"finite",
"nonfinite"
],
"title": "LatinVerbalParadigm",
"type": "object"
},
"NumberForms": {
"description": "A declension cell: the two number forms of one case. Latin forms are verbatim\n(macrons preserved); alternates stay space-separated as Wiktionary renders them.",
"properties": {
"singular": {
"title": "Singular",
"type": "string"
},
"plural": {
"title": "Plural",
"type": "string"
}
},
"required": [
"singular",
"plural"
],
"title": "NumberForms",
"type": "object"
},
"ParadigmNotFound": {
"description": "No inflection table for this page/POS (no Latin section, no table, or the\npage doesn't exist). ``found`` is False and there is no table body.",
"properties": {
"category": {
"const": "not_found",
"default": "not_found",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": false,
"default": false,
"title": "Found",
"type": "boolean"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class"
],
"title": "ParadigmNotFound",
"type": "object"
},
"SearchLanguage": {
"description": "The query language. ``lat`` looks a Latin word up directly (any of its forms —\nan inflected query resolves via the form index or Morpheus). ``eng`` searches in\nreverse: the English Wiktionary page for the query word lists per-sense Latin\ntranslations, and each distinct Latin lemma is then looked up normally.",
"enum": [
"lat",
"eng"
],
"title": "SearchLanguage",
"type": "string"
},
"Sense": {
"description": "One sense of an entry: the (HTML-stripped) Wiktionary definition line.",
"properties": {
"label": {
"default": "",
"title": "Label",
"type": "string"
},
"gloss": {
"title": "Gloss",
"type": "string"
},
"examples": {
"items": {
"type": "string"
},
"title": "Examples",
"type": "array"
},
"form_of": {
"default": "",
"description": "When this sense is a non-lemma inflected form ('accusative singular of aqua'), the lemma it inflects from — its Wiktionary page title, ready to search or feed to latin_get_inflections for the full paradigm. Empty for an ordinary gloss.",
"title": "Form Of",
"type": "string"
}
},
"required": [
"gloss"
],
"title": "Sense",
"type": "object"
},
"TranslationSense": {
"description": "One English sense (a translations table) and the Latin terms it offers.",
"properties": {
"sense": {
"description": "The sense gloss the source table carries.",
"title": "Sense",
"type": "string"
},
"terms": {
"items": {
"$ref": "#/$defs/TranslationTerm"
},
"title": "Terms",
"type": "array"
}
},
"required": [
"sense"
],
"title": "TranslationSense",
"type": "object"
},
"TranslationTerm": {
"description": "One Latin word a translations table offers for an English sense. ``word`` is\nthe Wiktionary page title (what an ``eng`` search re-searches and what\n``latin_get_inflections`` needs); ``display`` keeps the rendered text only when it\ndiffers (macrons: title 'uvidus' renders as 'ūvidus').",
"properties": {
"word": {
"description": "Wiktionary page title — the lemma itself.",
"title": "Word",
"type": "string"
},
"display": {
"default": "",
"description": "Rendered form when it differs from the title (macrons).",
"title": "Display",
"type": "string"
},
"gender": {
"default": "",
"description": "Grammatical gender as marked, e.g. 'f'.",
"title": "Gender",
"type": "string"
},
"qualifier": {
"default": "",
"description": "Usage qualifier as marked, e.g. 'poetic'; else empty.",
"title": "Qualifier",
"type": "string"
}
},
"required": [
"word"
],
"title": "TranslationTerm",
"type": "object"
}
},
"description": "The result of a dictionary search.",
"title": "SearchResult"
}🟢latin_get_inflections(entry_id, word_class)
Fetch the full declension (nominals) or conjugation (verbs) table for a lemma identified by a search result's inflection handle (entry_id + word_class). Use this only when a search ran without inline forms or left a match un-expanded — a default search already returns each match's table inline. Returns Markdown plus the table as structuredContent with the shape {"result": <paradigm>} per the declared outputSchema — switch on result.category ('nominal' | 'verbal' | 'not_found') before reading the body. Content from en.wiktionary.org (CC BY-SA 4.0).
入力スキーマ
{
"type": "object",
"properties": {
"entry_id": {
"description": "The Wiktionary page title (the lemma) from a search result's inflection handle, e.g. 'amo', 'aqua'.",
"maxLength": 80,
"minLength": 1,
"title": "Entry Id",
"type": "string"
},
"word_class": {
"description": "The part-of-speech section from a search result's inflection handle, e.g. 'verb', 'noun', 'adjective'.",
"maxLength": 24,
"minLength": 1,
"pattern": "^[a-z ]+$",
"title": "Word Class",
"type": "string"
}
},
"required": [
"entry_id",
"word_class"
],
"title": "latin_get_inflectionsArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"result": {
"discriminator": {
"mapping": {
"nominal": "#/$defs/LatinNominalParadigm",
"not_found": "#/$defs/ParadigmNotFound",
"verbal": "#/$defs/LatinVerbalParadigm"
},
"propertyName": "category"
},
"oneOf": [
{
"$ref": "#/$defs/LatinNominalParadigm"
},
{
"$ref": "#/$defs/LatinVerbalParadigm"
},
{
"$ref": "#/$defs/ParadigmNotFound"
}
],
"title": "Result"
}
},
"required": [
"result"
],
"$defs": {
"LatinNominalParadigm": {
"description": "Declension of a noun/adjective/etc.: case → {singular, plural}.\n\n``category`` discriminates this from the verbal and not-found shapes — switch on\nit before reading the body.",
"properties": {
"category": {
"const": "nominal",
"default": "nominal",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": true,
"default": true,
"title": "Found",
"type": "boolean"
},
"cases": {
"additionalProperties": {
"$ref": "#/$defs/NumberForms"
},
"description": "Case name (lower-case: 'nominative', 'genitive', …) → its singular/plural forms, in table order.",
"title": "Cases",
"type": "object"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class",
"cases"
],
"title": "LatinNominalParadigm",
"type": "object"
},
"LatinVerbalParadigm": {
"description": "Conjugation of a verb, grouped the way Wiktionary's table is:\nfinite cells keyed by \"<voice> <mood> <tense>\" → person/number → form, plus the\nnon-finite sections (infinitives, participles, gerund, supine).",
"properties": {
"category": {
"const": "verbal",
"default": "verbal",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": true,
"default": true,
"title": "Found",
"type": "boolean"
},
"finite": {
"additionalProperties": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"description": "'<voice> <mood> <tense>' (lower-case, e.g. 'active indicative present') → person/number ('first singular' … 'third plural') → the form. Periphrastic rows (e.g. passive perfect) appear under the single key 'all'. Alternates are comma-separated; an em-dash cell (no such form) is omitted.",
"title": "Finite",
"type": "object"
},
"nonfinite": {
"additionalProperties": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"description": "Non-finite section ('infinitive', 'participle', 'gerund', 'supine') → label ('active present', 'genitive', …) → the form.",
"title": "Nonfinite",
"type": "object"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class",
"finite",
"nonfinite"
],
"title": "LatinVerbalParadigm",
"type": "object"
},
"NumberForms": {
"description": "A declension cell: the two number forms of one case. Latin forms are verbatim\n(macrons preserved); alternates stay space-separated as Wiktionary renders them.",
"properties": {
"singular": {
"title": "Singular",
"type": "string"
},
"plural": {
"title": "Plural",
"type": "string"
}
},
"required": [
"singular",
"plural"
],
"title": "NumberForms",
"type": "object"
},
"ParadigmNotFound": {
"description": "No inflection table for this page/POS (no Latin section, no table, or the\npage doesn't exist). ``found`` is False and there is no table body.",
"properties": {
"category": {
"const": "not_found",
"default": "not_found",
"title": "Category",
"type": "string"
},
"entry_id": {
"title": "Entry Id",
"type": "string"
},
"word_class": {
"title": "Word Class",
"type": "string"
},
"found": {
"const": false,
"default": false,
"title": "Found",
"type": "boolean"
},
"source": {
"default": "Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing. (CC BY-SA 4.0)",
"title": "Source",
"type": "string"
}
},
"required": [
"entry_id",
"word_class"
],
"title": "ParadigmNotFound",
"type": "object"
}
},
"title": "latin_get_inflectionsOutput"
}🟢latin_lemmatize(word)
Analyze one inflected Latin form with the Morpheus morphological analyzer: its lemma(s) plus the grammatical reading (person, number, tense, mood, voice, case…). Useful when you want the morphology itself — for the dictionary entry, latin_search already resolves inflected queries on its own. Returns Markdown plus the analysis as structuredContent matching the declared outputSchema. Results are cached server-side. Analyses via the Perseids Morpheus service.
入力スキーマ
{
"type": "object",
"properties": {
"word": {
"description": "One inflected Latin word form to analyze, e.g. 'amavit', 'aquam'. Macrons optional.",
"maxLength": 80,
"minLength": 1,
"title": "Word",
"type": "string"
}
},
"required": [
"word"
],
"title": "latin_lemmatizeArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"word": {
"title": "Word",
"type": "string"
},
"found": {
"title": "Found",
"type": "boolean"
},
"analyses": {
"items": {
"$ref": "#/$defs/MorphAnalysis"
},
"title": "Analyses",
"type": "array"
},
"source": {
"default": "Morpheus morphological analyses via the Perseids Project morphology service (morph.perseids.org), Tufts University / Perseus Digital Library.",
"title": "Source",
"type": "string"
}
},
"required": [
"word",
"found"
],
"$defs": {
"MorphAnalysis": {
"description": "One Morpheus analysis of an inflected form: its lemma plus the grammatical\ntags the analyzer assigned (mood/tense/case/number/…, whatever applies).",
"properties": {
"lemma": {
"title": "Lemma",
"type": "string"
},
"part_of_speech": {
"default": "",
"title": "Part Of Speech",
"type": "string"
},
"tags": {
"additionalProperties": {
"type": "string"
},
"title": "Tags",
"type": "object"
},
"source": {
"default": "Morpheus morphological analyses via the Perseids Project morphology service (morph.perseids.org), Tufts University / Perseus Digital Library.",
"title": "Source",
"type": "string"
}
},
"required": [
"lemma"
],
"title": "MorphAnalysis",
"type": "object"
}
},
"description": "The result of lemmatizing one word form via Morpheus.",
"title": "Lemmatization"
}コミュニティ
エビデンス