How do I use jun-skills-hwpx-v2?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@jun-skills-hwpx-v2 Turn 'meeting.md' into a HWPX document." 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.

jun-skills-hwpx-v2

by cjLee-cmd

Overview Schema Source Related Servers Discussions Admin

Python

Local

jun-skills-hwpx-v2

Unified HWPX (Hangul Word Processor) MCP Server

Markdown 문서를 HWPX로 변환하거나, 기존 HWPX 템플릿을 분석하여 서식을 유지하면서 새로운 내용으로 문서를 생성하는 통합 MCP 서버입니다.

Copyright (c) 2026 이창준, (주)파워솔루션 | MIT License

두 가지 워크플로우

1. Markdown → HWPX (템플릿 불필요)

Markdown 파일을 바로 HWPX 문서로 변환합니다. 표지, 머리글/바닥글, 자동 번호 매기기를 지원합니다.

"report.md를 한글 문서로 변환해줘"

사용 도구: convert_md_to_hwpx

2. HWPX 템플릿 → HWPX (서식 유지)

기존 HWPX 문서의 서식(글꼴, 여백, 스타일)을 그대로 유지하면서 내용만 교체합니다. 공문, 보고서, 회의록 등 정해진 양식이 있을 때 사용합니다.

"이 공문 양식에 맞춰서 새 문서를 만들어줘"

사용 도구: analyze_hwpx → extract_hwpx_xml → build_hwpx → validate_hwpx → page_guard_hwpx

Related MCP server: doc-ops-mcp

설치

자동 설치 (권장)

macOS / Linux:

curl -LsSf https://raw.githubusercontent.com/cjLee-cmd/jun-skills-hwpx-v2/main/install.sh | bash

Windows (PowerShell):

Invoke-WebRequest -Uri "https://raw.githubusercontent.com/cjLee-cmd/jun-skills-hwpx-v2/main/install.bat" -OutFile "$env:TEMP\install.bat"; & "$env:TEMP\install.bat"

설치 스크립트가 자동으로 수행하는 작업:

uv 설치 (없는 경우)
소스 다운로드 (~/jun-skills-hwpx-v2)
의존성 설치 (uv sync)
MCP 서버 자동 등록:
- Claude Code (~/.claude.json)
- Claude Desktop (claude_desktop_config.json)
- Gemini CLI (~/.gemini/settings.json)

수동 설치

git clone https://github.com/cjLee-cmd/jun-skills-hwpx-v2.git ~/jun-skills-hwpx-v2
cd ~/jun-skills-hwpx-v2
uv sync

MCP 설정 파일에 다음을 추가:

{
  "mcpServers": {
    "hwpx": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/jun-skills-hwpx-v2", "python", "scripts/mcp_server.py"]
    }
  }
}

클라이언트	설정 파일 경로
Claude Code	`~/.claude.json`
Claude Desktop (macOS)	`~/Library/Application Support/Claude/claude_desktop_config.json`
Claude Desktop (Windows)	`%APPDATA%\Claude\claude_desktop_config.json`
Gemini CLI	`~/.gemini/settings.json`

MCP 도구 목록

도구	설명
`convert_md_to_hwpx`	Markdown → HWPX 변환 (표, 코드블록, 리스트, 인용문, 표지, 머리글/바닥글 지원)
`analyze_hwpx`	HWPX 문서 구조 분석 (글꼴, 스타일, 레이아웃 추출)
`extract_hwpx_xml`	HWPX에서 header.xml / section0.xml 추출
`build_hwpx`	템플릿 + XML → HWPX 조립
`validate_hwpx`	HWPX 구조 무결성 검증
`page_guard_hwpx`	레퍼런스 대비 페이지 수 드리프트 검사
`extract_text_hwpx`	HWPX에서 텍스트 추출

CLI 직접 실행

cd ~/jun-skills-hwpx-v2

# Markdown → HWPX
uv run python scripts/md2hwpx.py input.md output.hwpx --title "보고서 제목"

# HWPX 분석
uv run python scripts/analyze_template.py template.hwpx

사용 예시

Claude / Gemini에서 사용

# Markdown → HWPX (템플릿 없이)
"이 마크다운 파일을 한글 문서로 변환해줘"
"report.md를 HWPX로 만들어줘. 제목은 '월간 보고서'"

# HWPX 템플릿 기반
"이 한글 문서를 분석해줘" (analyze_hwpx)
"이 양식에 맞춰 새 문서를 만들어줘" (전체 워크플로우)
"공문 양식으로 문서를 작성해줘" (내장 템플릿 사용)

내장 템플릿

templates/ 폴더에 다음 양식이 포함되어 있습니다:

템플릿	설명
`base/`	기본 스켈레톤
`gonmun/`	공문
`report/`	보고서
`minutes/`	회의록
`proposal/`	제안서

요구 사항

Python 3.10+
uv (설치 스크립트가 자동 설치)
git

라이선스

MIT License - 자유롭게 사용, 수정, 배포할 수 있습니다.

Available Tools

7 tools

analyze_hwpxA

Analyze an existing HWPX file and return its full structure.

Outputs font definitions, border/fill styles, character styles (charPr), paragraph styles (paraPr), page/margin settings, and the complete body structure including all paragraphs and tables with cell details.

Use this as the first step when the user provides a reference HWPX file for replication or editing.

Inputs: hwpx_path (required). Returns: result

build_hwpxA

Build an HWPX file from a template and optional XML overrides.

Workflow:

Start from the base template skeleton.
Optionally overlay a document-type template (gonmun/report/minutes).
Optionally override header.xml (styles) and/or section0.xml (body).
Pack as a valid HWPX archive and validate.

When a user provides a reference HWPX, first call analyze_hwpx() and extract_hwpx_xml() to get the header/section XML, then write a new section0.xml with only the required text changes, and pass it here.

Inputs: output_hwpx (required), title, creator, template, +2 more. Returns: result

convert_md_to_hwpxA

Convert a Markdown file to HWPX format.

Use this when the user wants to create an HWPX document from a Markdown file WITHOUT providing a reference HWPX template. Generates a complete document with cover page, page headers/footers, heading auto-numbering, native tables, code blocks, lists, and blockquotes.

Inputs: input_md (required), output_hwpx (required), title, author, +1 more. Returns: result

extract_hwpx_xmlA

Extract header.xml and section0.xml from an HWPX file.

Use this to get the raw XML from a reference HWPX so you can:

Read the exact charPrIDRef/paraPrIDRef/borderFillIDRef values in use
Copy the header.xml for reuse in build_hwpx()
Edit section0.xml text nodes and pass the modified file to build_hwpx()

Inputs: hwpx_path (required), extract_dir. Returns: result

extract_text_hwpxB

Extract plain text content from an HWPX file.

Inputs: hwpx_path (required), fmt, include_tables. Returns: result

page_guard_hwpxA

Check that output HWPX has not drifted in page count vs a reference.

Best for SAME-STRUCTURE edits (filling values into a form, replacing text in-place without adding/removing paragraphs or tables). When sections are added, removed, or restructured, expected differences will be reported as failures — in that case use validate_hwpx for integrity checks instead.

Compares paragraph count, table count, table dimensions, explicit page/column breaks, and overall text length between reference and output.

Inputs: output_hwpx (required), reference_hwpx (required), max_text_delta, max_paragraph_delta. Returns: result

validate_hwpxA

Validate the structural integrity of an HWPX file.

Checks: valid ZIP, required files, mimetype content/position/compression, and XML well-formedness.

Inputs: hwpx_path (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-08-10 05:20 across 7 tools

Disambiguation5/5

Each tool targets a distinct operation: validation, conversion from Markdown, structure analysis, template-based building, raw XML extraction, page-count verification, and plain text extraction. No two tools have overlapping purposes, and the descriptions clearly differentiate them.

Naming Consistency3/5

Most tools follow a verb_hwpx pattern (validate_hwpx, analyze_hwpx, build_hwpx), but convert_md_to_hwpx and extract_hwpx_xml deviate. The extract_hwpx_xml and extract_text_hwpx tools especially have inconsistent ordering of source/object (hwpx before xml vs. after text). While all names start with a verb, the overall pattern is not uniform.

Tool Count5/5

With 7 tools covering creation, analysis, extraction, validation, and page-count verification, the count is well-scoped for an HWPX manipulation server. Each tool earns its place without redundancy or bloat.

Completeness5/5

The tool set provides full lifecycle coverage: create (convert_md_to_hwpx, build_hwpx), read/analyze (analyze_hwpx, extract_hwpx_xml, extract_text_hwpx), and verify (validate_hwpx, page_guard_hwpx). Editing is achievable via the build_hwpx workflow with extracted XML, leaving no obvious gaps.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

MdkitA
online.mdkit
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Developer Tools RAG Systems Data Platforms
1
https://api.mdkit.online/mcp/
doc-convert-mcpA
io.github.Anon2052
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Image & Video Processing Data Platforms File Systems
41
https://doc-convert-mcp.onrender.com/mcp/
stagenth · 文档生成A
com.stagenth
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
File Systems Workplace & Productivity
3
https://stagenth.com/mcp/doc-gen/
flatmarkA
dev.flatmark
Document to Markdown MCP server: PDF, Word, PowerPoint, Excel and HTML, with OCR for large files.
Documentation Access Image & Video Processing Workplace & Productivity
31
https://api.flatmark.dev/mcp/

Related MCP Servers

mcp-pandoc
File Systems Developer Tools Multimedia Processing
vivekVells
A
license
A
quality
C
maintenance
MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, PDF, DOCX (.docx), csv and more.
Updated 3 months ago (2026-08-15 21:24 UTC)
1
587
MIT
doc-ops-mcp
Documentation Access Content Management Systems
Tele-AI
A
license
B
quality
D
maintenance
A universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.
Updated 5 days ago (2026-11-09 09:08 UTC)
13
18 npm
140
MIT
hwpConverMdMCP
File Systems Developer Tools App Automation
beomzh
F
license
A
quality
D
maintenance
An MCP server that enables LLMs to convert HWP and HWPX documents into Markdown for analysis and processing. It supports document conversion via local file paths or Base64 content across various MCP-compatible clients.
Updated 8 months ago (2026-03-13 04:05 UTC)
2
-
md2pdf-mcp
Workplace & Productivity Developer Tools
chunliu
A
license
Not graded
quality
D
maintenance
MCP Server for Markdown to PDF conversion.
Updated a year ago (2025-10-13 06:13 UTC)
MIT

jun-skills-hwpx-v2

두 가지 워크플로우

1. Markdown → HWPX (템플릿 불필요)

2. HWPX 템플릿 → HWPX (서식 유지)

설치

자동 설치 (권장)

수동 설치

MCP 도구 목록

CLI 직접 실행

사용 예시

Claude / Gemini에서 사용

내장 템플릿

요구 사항

라이선스

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

mcp-pandoc

doc-ops-mcp

hwpConverMdMCP

md2pdf-mcp