Hwp MCP
A server that allows LLM to read and write HWP documents through the MCP protocol, and realizes document operation functions by bridging and calling the HWP COM API through PowerShell
2.5 points
5.7K

What is HWP MCP Server?

HWP MCP Server is an intelligent document processing tool specifically designed to handle the HWP document format (Hangul documents), which is the standard in South Korea. It allows you to use natural - language conversations to have an AI assistant perform various document operations, such as opening documents, editing content, formatting text, creating tables, and inserting pictures.

How to use HWP MCP Server?

You only need to configure the server in an AI assistant that supports the MCP protocol (such as Claude Desktop), and then you can operate HWP documents just like having a conversation with the assistant. Tell the assistant what you want to do, such as 'Open my report document', 'Bold the second paragraph', 'Insert a table on the third page', and the assistant will automatically complete these operations.

Applicable scenarios

Suitable for users who need to process HWP documents frequently, especially those who need to process multiple documents in batches, automate repetitive document operations, are not familiar with the complex operation interface of HWP software, or hope to quickly complete document editing tasks through natural language.

Main features

Document management
Supports opening, closing, and saving HWP documents. It can handle multiple documents simultaneously and supports saving as different formats (HWP, PDF, DOCX, etc.).
Text editing
Basic editing functions such as reading the full text of the document, searching and replacing text, inserting and deleting content, and getting a list of paragraphs.
Format setting
Set font styles (size, color, bold, etc.), paragraph formats (alignment, line spacing), page styles (margins, orientation), etc.
Table operations
Create tables, add and delete rows and columns, merge and split cells, set table styles, extract table data, etc.
Advanced features
Professional functions such as batch file conversion, setting document security permissions, inserting bookmarks and hyperlinks, generating a table of contents, and mail merging.
Cursor navigation
Precise positioning functions such as precisely controlling the cursor position, getting and setting cursor coordinates, selecting text ranges, and document scanning.
Field management
Create and manage template fields (placeholders), batch - fill field content, modify field attributes, etc.
Images and formulas
Insert images and background images, create mathematical formulas, set image attributes, etc.
Printing and exporting
Output functions such as printing documents, setting watermarks, exporting to image formats, and batch - converting documents.
Advantages
Natural - language operation: No need to learn complex software interfaces. Complete document operations through conversations.
Comprehensive functions: Covers 100% of the 199 parameter sets of the HWP COM API.
Batch processing: Supports automated operations such as batch conversion and batch filling.
Cross - format support: Supports conversion between multiple formats such as HWP, PDF, and DOCX.
Precise control: Provides detailed cursor positioning and selection control.
Limitations
Only available on Windows systems: The HWP COM API can only run on Windows.
Requires Hangul software installation: You must install Hancom Office Hangul to use it.
Only supports binary HWP: HWPX (XML format) requires a separate server support.
Technical requirements: Some technical knowledge is required for initial configuration.

How to use

Install necessary software
Make sure you have installed Hancom Office Hangul software on your Windows computer. This is a prerequisite for using the HWP COM API.
Install Python environment
Install Python 3.11 or a higher version, and use the uv package manager to install HWP MCP Server.
Configure the AI assistant
Add server configuration in an AI assistant that supports MCP, such as Claude Desktop, and specify the execution path of HWP MCP Server.
Start using
Start the AI assistant and begin to operate HWP documents through natural - language conversations.

Usage examples

Document content extraction
Extract key information from multiple HWP reports and summarize them
Batch format adjustment
Uniformly modify the format styles of multiple documents
Table data processing
Extract data from the document table and process it
Document template filling
Use data to batch - fill document templates

Frequently Asked Questions

Can I use this tool on Mac or Linux?
What version of Hangul software do I need to install?
Is this tool safe? Will it damage my documents?
Which file formats does it support for conversion?
Can it handle multiple documents simultaneously?
Do I need programming knowledge to use it?

Related resources

GitHub repository
Project source code and the latest version
Hangul official documentation
Official documentation and download of Hancom Office Hangul
MCP protocol documentation
Official specification of the Model Context Protocol
Python installation guide
Official Python download and installation tutorial
Claude Desktop configuration
Usage and configuration guide for Claude Desktop

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "hwp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/hwp-mcp", "hwp-mcp"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.2K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
7.3K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.7K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.0K
4 points
P
Paperbanana
Python
7.6K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
8.8K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
8.3K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
8.4K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
37.6K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
27.2K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
22.8K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
76.1K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
35.7K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
66.7K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.4K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
101.0K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase