用 zhtw-mcp 搭配 AI 寫出更像台灣人的中文 | Write Taiwanese Mandarin: zhtw-mcp as a Linguistic Linter for Traditional Chinese

大型語言模型產生的繁體中文，常混入中國用語、過度簡化的漢語、錯誤標點與不精準術語，這些輸出會在文件、教學、開放原始碼專案與技術文章中逐漸污染書寫習慣。zhtw-mcp 是個透過 Model Context Protocol (MCP) 整合到 AI 助理的繁體中文書寫檢查器，可依中華民國教育部標點、國字標準字體與兩岸詞彙差異，檢查並修正 AI 產生的中文。

本議程介紹為什麼 AI 中文輸出容易被不精準來源混雜影響，如何將中文潤稿轉化為可測試、可重現、可融入進開發流程的工程議題，並展示 zhtw-mcp 如何自動改善台灣繁體中文書寫材料的品質和文化傳承。

LLMs often generate Traditional Chinese that looks fluent but mixes zh-CN vocabulary, Simplified-Chinese phrasing, inconsistent punctuation, and unstable technical terminology. zhtw-mcp turns this problem into an engineering workflow: a Model Context Protocol server that checks, fixes, and gates zh-TW text using Taiwan-specific language rules.

This talk presents the design of zhtw-mcp, the challenges of handling ambiguous terminology and false friends, and how linguistic linting can be integrated into AI-assisted writing, documentation, teaching material, and open-source development workflows.