kanji_to_romaji

Instructions

Implementation Reference

• src/japan_utils_mcp/server.py:177-208 (handler)

  The tool handler function for 'kanji_to_romaji'. Uses pykakasi to convert Japanese text (kanji + kana) to Hepburn romaji and hiragana.

  @mcp.tool()
  def kanji_to_romaji(text: str) -> dict[str, Any]:
      """Transliterate Japanese text (kanji + kana mix) to Hepburn romaji.
  
      Args:
          text: Japanese text. May contain kanji, hiragana, katakana, ASCII.
              Non-Japanese characters pass through unchanged.
  
      Returns:
          dict with keys:
              - romaji: str (space-separated Hepburn romaji)
              - hiragana: str (kanji converted to hiragana, kana preserved)
              - input: str (echo of the original input)
  
      Examples:
          kanji_to_romaji("山田太郎") → {"romaji": "yamada tarou", "hiragana": "やまだたろう"}
          kanji_to_romaji("東京駅") → {"romaji": "toukyou eki", "hiragana": "とうきょうえき"}
  
      Caveats:
          - Kanji with multiple readings (e.g. proper nouns) may be ambiguous.
            The transliteration uses the most common reading, which is
            sometimes wrong for personal names. Use as a starting point, not a
            guarantee.
      """
      results = _kakasi.convert(text)
      romaji = " ".join(r["hepburn"] for r in results if r["hepburn"]).strip()
      hira = "".join(r["hira"] for r in results)
      return {
          "romaji": romaji,
          "hiragana": hira,
          "input": text,
      }

• src/japan_utils_mcp/server.py:174-174 (helper)

  The pykakasi instance used as the engine for transliteration. Initialized at module level.

  _kakasi = pykakasi.kakasi()

• src/japan_utils_mcp/server.py:177-177 (registration)

  The tool is registered via the @mcp.tool() decorator on the kanji_to_romaji function. mcp is a FastMCP instance created on line 28.

  @mcp.tool()

• src/japan_utils_mcp/server.py:177-208 (schema)

  The function signature defines the schema: input is 'text: str', output is dict with keys 'romaji', 'hiragana', and 'input'. Docstring describes the expected behavior.

  @mcp.tool()
  def kanji_to_romaji(text: str) -> dict[str, Any]:
      """Transliterate Japanese text (kanji + kana mix) to Hepburn romaji.
  
      Args:
          text: Japanese text. May contain kanji, hiragana, katakana, ASCII.
              Non-Japanese characters pass through unchanged.
  
      Returns:
          dict with keys:
              - romaji: str (space-separated Hepburn romaji)
              - hiragana: str (kanji converted to hiragana, kana preserved)
              - input: str (echo of the original input)
  
      Examples:
          kanji_to_romaji("山田太郎") → {"romaji": "yamada tarou", "hiragana": "やまだたろう"}
          kanji_to_romaji("東京駅") → {"romaji": "toukyou eki", "hiragana": "とうきょうえき"}
  
      Caveats:
          - Kanji with multiple readings (e.g. proper nouns) may be ambiguous.
            The transliteration uses the most common reading, which is
            sometimes wrong for personal names. Use as a starting point, not a
            guarantee.
      """
      results = _kakasi.convert(text)
      romaji = " ".join(r["hepburn"] for r in results if r["hepburn"]).strip()
      hira = "".join(r["hira"] for r in results)
      return {
          "romaji": romaji,
          "hiragana": hira,
          "input": text,
      }