I built a self-hosted AI knowledge base on top of offline Wikipedia (and it speaks MCP)

Описание и применение

Zim Pro заменяет kiwix‑serve, позволяя выполнять полнотекстовый поиск, задавать вопросы LLM‑м, автоматически обновлять ZIM‑файлы и использовать библиотеку как источник данных в офлайн‑режиме.

Задача

The existing kiwix-serve tool only allows reading offline ZIM files; the author needed to query the content, keep it updated automatically, and use it as a source for local LLMs.

Результат

Zim Pro enables offline querying of large ZIM libraries with AI-generated answers, automatic updates, and integration with local LLMs, all without internet access.

Рабочий процесс

• 1. Install Zim Pro via Docker or pip.
• 2. Mount ZIM files into the /data volume or add them via the built-in catalog.
• 3. Start the server and access http://localhost:8083 to browse and search.
• 4. Use the MCP command claude mcp add --transport http zim-pro http://localhost:8083/mcp to expose tools to Claude.
• 5. Query the library with AI tools; Zim Pro performs plan, deep search, light search, and rank steps to retrieve relevant passages.
• 6. The AI answers are repaired for Markdown correctness before display.

Доказательства

On my home server I have a folder containing ZIM files: these are offline versions of Wikipedia, Stack Exchange, DevDocs and iFixit, all drawn from the Kiwix catalog.

Источник

The problem was that kiwix-serve only allows you to read it. What I wanted to do was: ask it questions and get answers I could verify, keep the books updated without checking for new releases by hand, have my other AI tools (Claude, the local LLMs) use it as a source.

Источник

Zim Pro makes use of the full-text index that is already contained in each ZIM file and places the intelligence around that index: Plan, Deep search, Light search, Rank.

Источник

The available tools are list_books, search, suggest, get_article, get_article_outline and list_updates.

Источник