Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@hwpx-mcp-server Extract all text from 'meeting_minutes.hwpx' and summarize it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for reading and editing .hwpx (Hangul Word Processor) files.
Tool | Description |
| Extract all text from a .hwpx file |
| Find and replace text |
| Change font/size/bold/italic/underline |
| Create a new .hwpx file |
Related MCP server: HWP-MCP
npm install
npm run buildAdd to your ~/.gemini/settings.json:
{
"mcpServers": {
"hwpx": {
"command": "node",
"args": ["/absolute/path/to/hwpx-mcp-server/dist/index.js"]
}
}
}npm run dev # watch mode
npm run build # compile TypeScript
npm start # run serverHWPX is a ZIP-based XML format:
doc.hwpx (ZIP)
├── mimetype # must be first, uncompressed
├── META-INF/container.xml
└── Contents/
├── content.hpf # manifest
└── section0.xml # body text (hp:t tags)HWPX only (not legacy binary .hwp)
Style editing uses regex-based XML patching — open in 한글 to verify layout
mimetype entry must remain uncompressed (ZIP store method)
This server cannot be deployed
자동화하여 HWPX 문서의 로딩, 탐색, 편집, 검증을 한 번에 처리합니다. 문단·표·주석 추가, 텍스트 일괄 치환, 머리말·꼬리말 설정 등 반복 작업을 신속히 수행합니다. 기…
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
