hwp-mcp — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by treesoop · MCP Server · ★ 68

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is hwp-mcp safe to install? View the security audit →

About hwp-mcp

hwp-mcp Claude · Cursor · ChatGPT 등 MCP 호환 AI에서 한글 문서(.hwp / .hwpx) 를 읽고 수정하고 새로 만들 수 있게 해주는 서버입니다. 은 한컴오피스 문서를 AI 에이전트가 직접 다루도록 해주는 MCP(Model Context Protocol) 서버입니다. 읽기뿐 아니라 텍스트 수정, 템플릿 채우기, 새 문서 생성까지 가능합니다. 어떤 프로젝트인가요? 이 프로젝트는 두 부분으로 나뉩니다. 🔧 rhwp가 한 일 (핵심 엔진) — Edward Kim 님의 rhwp는 닫힌 한글 포맷(HWP 5.0 binary, HWPX/OWPML)을 전부 역공학으로 풀어 Rust + WebAssembly로 구현한 오픈소스 엔진입니다. 파싱, 표·이미지·수식·머리말 추출, SVG 렌더링, 한컴 호환 Field API — 이 모든 핵심 능력은 rhwp 가 제공합니다. rhwp 가 없으면 이 프로젝트도 없습니다. 🤝 가 한 일 (에이전트 어댑터) — 위에 얹은 얇은 MCP 서버 layer. 우리가 추가한 것은: , , 같은 에이전트 친화적 도구 시그니처 — Claude/Cursor 같은 LLM이 자연어로 호출할 수 있게 본문·표·이미지·머리말·꼬리말·각주·수식을 한 번에 dump 하는 시나리오 중심 traversal walker 표 셀 병합 자동 처리, footnote/equation 자동 합본 같은 사용 편의 layer rhwp 0.7.7 의 라운드트립 한

ai-agentclaudecursorhancomhancom-officehangulhwphwpxkoreanllm

Quick Facts

Stars68
Forks10
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score66.0775624540118/100
Last Updated2026-07-08
Created2026-03-31
Platformsclaude-code, mcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with hwp-mcp for enhanced workflows:

  • sidekick-dev-web — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)
  • ungate — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (51%)

hwp-mcp alternative? Top 6 similar tools

Looking for a hwp-mcp alternative? If you're comparing hwp-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claw-hwp by DoHyun468 · ⭐ 162

    AI(Claude·클로드 · Codex·코덱스)로 한글 문서(.hwp/.hwpx)를 한컴 없이 읽고·만들고·편집하는 오픈소스 스킬 · Read, create & edit Korean HWP in C

  • google-analytics-mcp by surendranb · ⭐ 242

    Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to

  • deterministic-agent-control-protocol by elliot35 · ⭐ 89

    Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT

  • youtube-connector-mcp by ShellyDeng08 · ⭐ 73

    MCP server for YouTube — search videos, get transcripts, channels, and playlists. Works with Claude, Cursor &

  • vscode-mcp by tjx666 · ⭐ 103

    MCP server for Claude Code/VSCode/Cursor/Windsurf to use editor self functionality. ⚡ Get real-time LSP diagno

  • python-hwpx-automation by airmang · ⭐ 68

    MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is hwp-mcp?

hwp-mcp is MCP server for reading and writing HWP/HWPX (Korean Hangul) documents — built on rhwp. 34 tools, Claude/Cursor/ChatGPT compatible.. It is categorized as a MCP Server with 68 GitHub stars.

What programming language is hwp-mcp written in?

hwp-mcp is primarily written in TypeScript. It covers topics such as ai-agent, claude, cursor.

How do I install or use hwp-mcp?

You can find installation instructions and usage details in the hwp-mcp GitHub repository at github.com/treesoop/hwp-mcp. The project has 68 stars and 10 forks, indicating an active community.

What license does hwp-mcp use?

hwp-mcp is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to hwp-mcp?

The top alternatives to hwp-mcp on Agent Skills Hub include claw-hwp, google-analytics-mcp, deterministic-agent-control-protocol. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools