Japanese Skills · 言の葉

Working · 3.3 s

io.github.Keith-CY/japaneseskills-mcpv1.0.0

Japanese words with pitch accent and conjugation, kanji and grammar for JLPT learners.

Education

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://japaneseskills.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

find_grammar Read-only

Use this when the user asks about a Japanese grammar pattern or particle (〜てもいい, ために, ば vs たら, は and が), what it means, how it is used, an example of it, or how to say something with a pattern. Searches the site’s 828 grammar points (N5–N1) by the pattern in Japanese or romaji, or by its meaning in the user’s language. Each result has the pattern, JLPT level, meaning in the user’s language, an example sentence with translation, a recording of the example where available, and the grammar page; plus the site’s course lessons whose titles match, with links and whether each is free or needs a subscription or pass.

querystring, required

The pattern (てもいい, 〜ために, te mo ii) or what it expresses in the user’s language (permission, “in order to”, 为了).

langstring

The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.

levelstring

Only this JLPT level.

limitinteger

How many grammar points to return at most.

Tools (4)

find_grammar

read-only

Argument	Type	Description
lang	string	The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.
level	string	Only this JLPT level.
limit	integer	How many grammar points to return at most.
query*	string	The pattern (てもいい, 〜ために, te mo ii) or what it expresses in the user’s language (permission, “in order to”, 为了).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "lang": {
      "enum": [
        "zh-Hans",
        "zh-Hant",
        "en",
        "ko"
      ],
      "type": "string",
      "description": "The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query."
    },
    "level": {
      "enum": [
        "N5",
        "N4",
        "N3",
        "N2",
        "N1"
      ],
      "type": "string",
      "description": "Only this JLPT level."
    },
    "limit": {
      "type": "integer",
      "default": 4,
      "maximum": 10,
      "minimum": 1,
      "description": "How many grammar points to return at most."
    },
    "query": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "The pattern (てもいい, 〜ために, te mo ii) or what it expresses in the user’s language (permission, “in order to”, 为了)."
    }
  },
  "additionalProperties": false
}

list_courses

Use this when the user asks how to study Japanese or prepare for a JLPT level with Japanese Skills · 言の葉, or what study material the site has. Lists the study library (sections, counts and links), the JLPT practice levels (number of questions; links for the free ones), and the 15 courses with their level, number of lessons and link. With course, lists that course’s lessons with titles and links. Each level, course and lesson is labelled free or needs a subscription or pass.

read-only

Argument	Type	Description
lang	string	The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.
course	string	A course id from this tool’s list (e.g. "n5", "kanji", "keigo") to list its lessons.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "lang": {
      "enum": [
        "zh-Hans",
        "zh-Hant",
        "en",
        "ko"
      ],
      "type": "string",
      "description": "The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query."
    },
    "course": {
      "type": "string",
      "maxLength": 20,
      "description": "A course id from this tool’s list (e.g. \"n5\", \"kanji\", \"keigo\") to list its lessons."
    }
  },
  "additionalProperties": false
}

lookup_kanji

Use this when the user asks about a kanji (a Chinese character used in Japanese): which JLPT words use it and how it is read in them, at which JLPT level it first appears, or where to learn it. For each kanji given (up to five), lists the words in the site’s JLPT word list that contain it, easiest level first, with reading, level and meaning in the user’s language; how many words use it and the lowest level among them; and the site’s kanji lessons that teach it (title, link, and whether each is free or needs a subscription or pass). Gives no on’yomi/kun’yomi table or stroke order: the readings are those of the words.

read-only

Argument	Type	Description
lang	string	The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.
kanji*	string	One to five kanji, e.g. "生" or "日本".
limit	integer	How many words to list per kanji at most.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "kanji"
  ],
  "properties": {
    "lang": {
      "enum": [
        "zh-Hans",
        "zh-Hant",
        "en",
        "ko"
      ],
      "type": "string",
      "description": "The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query."
    },
    "kanji": {
      "type": "string",
      "maxLength": 20,
      "minLength": 1,
      "description": "One to five kanji, e.g. \"生\" or \"日本\"."
    },
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 20,
      "minimum": 1,
      "description": "How many words to list per kanji at most."
    }
  },
  "additionalProperties": false
}

lookup_word

Use this when the user asks about a Japanese word: what it means, how to read or pronounce it, its pitch accent, whether it is a godan or ichidan verb, how to conjugate it (te-form, past, polite, potential…), or how to say something in Japanese. Searches the 9,040 JLPT words (N5–N1) of Japanese Skills · 言の葉 by the word in kanji or kana (食べる, たべる), romaji (taberu), or a meaning in English, Chinese or Korean (eat, 吃, 먹다). Each result has the reading, JLPT level, the meaning in the user’s language, the pitch accent (accent number, type and H/L pattern), the word class and conjugation table where the site has one, an example sentence with its translation where the site has one, recordings in two voices where available, and the word’s page. Shows a word card in chats that display app UI. Returns no results when the word is not in the list. Not for translating whole sentences.

read-only

Argument	Type	Description
lang	string	The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.
level	string	Only this JLPT level.
limit	integer	How many matches to return at most.
query*	string	One word: Japanese (食べる, たべる, タベル), romaji (taberu), or a meaning in the user’s language (eat, 吃, 먹다).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "lang": {
      "enum": [
        "zh-Hans",
        "zh-Hant",
        "en",
        "ko"
      ],
      "type": "string",
      "description": "The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query."
    },
    "level": {
      "enum": [
        "N5",
        "N4",
        "N3",
        "N2",
        "N1"
      ],
      "type": "string",
      "description": "Only this JLPT level."
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 10,
      "minimum": 1,
      "description": "How many matches to return at most."
    },
    "query": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "One word: Japanese (食べる, たべる, タベル), romaji (taberu), or a meaning in the user’s language (eat, 吃, 먹다)."
    }
  },
  "additionalProperties": false
}