Hwpx MCP
The enhanced version of the HWPX MCP server is a cross - platform AI document editing tool that supports automatic reading, writing, and editing of Korean documents in HWPX format through the MCP protocol. It solves the key bugs in the original project and adds advanced functions such as nested tables and Mermaid charts.
rating : 2.5 points
downloads : 0
What is HWPX MCP Server?
This is a server based on the Model Context Protocol (MCP), specifically designed to handle the HWPX file format. HWPX is the modern XML version of the widely used Korean document format (.hwp). This server allows AI assistants like Claude to directly open, read, edit, and save HWPX documents, achieving automation of document processing.How to use HWPX MCP Server?
First, you need to configure this server in an AI client that supports MCP (such as Claude Desktop, Cursor, VS Code, etc.). After configuration, the AI assistant can operate on HWPX documents through 77 dedicated tool commands, such as modifying text, editing tables, inserting pictures, or adjusting formats.Applicable scenarios
Suitable for scenarios that require batch processing or automated editing of HWPX documents, such as automatically generating reports, batch - updating information in contract templates, filling data tables into fixed - format documents, adding unified headers and footers to documents, etc. It is especially suitable for processing Korean documents in cross - platform (Windows, macOS, Linux) environments.Main features
Full - platform support
You can process HWPX documents on Windows, macOS, and Linux through Node.js without installing Korean office software. The generated documents can be opened normally in Korean office software on the corresponding platforms.
Complete document management
It provides basic operations such as creating, opening, closing, and saving documents, and supports backup and file integrity verification to ensure operation safety.
Rich editing functions
It supports reading and editing of almost all HWPX document elements, such as text, paragraphs, tables, pictures, shapes, headers and footers, comments, hyperlinks, and formulas.
Advanced table operations
It supports creating, modifying, and deleting tables, rows, and columns. You can even create 'tables within tables' (nested tables) and precisely modify the content of specific cells.
Intelligent search and replacement
It supports text search in the full text (including within table cells) and can perform precise replacement for specific table cells to avoid incorrect modifications.
Mermaid chart insertion
You can directly render Mermaid code (such as flowcharts and sequence diagrams) as pictures and insert them into the document, which is convenient for writing technical documents.
Perfect style preservation
When editing text or tables, all original formats such as fonts, colors, and spacing will be automatically retained to avoid document style confusion.
Advantages
High automation efficiency: Repetitive document editing tasks can be completed quickly through AI assistants.
Cross - platform compatibility: It solves the problem of processing HWPX files on non - Windows systems.
Comprehensive functions: It provides 77 tools, covering most document editing needs.
Stable and reliable: The enhanced version fixes many key bugs in the original version, such as file corruption and text overlapping.
No graphical interface required: It can be operated entirely through the command line and API, suitable for integration into automated processes.
Limitations
Only supports the HWPX format: It does not support the old binary.hwp format and requires conversion using Korean office software first.
Requires technical configuration: Users need to correctly configure the server path in the MCP client.
Depends on AI clients: It must be used through tools that support MCP, such as Claude and Cursor.
Complex format preview: The final typesetting effect still needs to be checked and confirmed in Korean office software.
How to use
Install the server
Clone the project from GitHub, enter the `mcp - server` directory, and run `npm install` and `npm run build` to install dependencies and build the server.
Configure the MCP client
According to the AI client you are using (such as Claude Desktop, Cursor), edit its MCP configuration file and add the path to the server script you just built.
Restart the client and verify
Restart your AI client (such as Claude Desktop). After a successful connection, you should see 'hwpx - mcp' and its many provided tools in the client's tool list.
Start editing documents
Use the `open_document` tool to open an HWPX file, and then you can use other tools (such as `update_table_cell`, `insert_image`) to edit it. After the operation is completed, use `save_document` to save.
Usage examples
Example 1: Batch - update data in monthly reports
A monthly sales report HWPX document with a fixed format needs to be generated, and only the data table in it needs to be updated.
Example 2: Add a system architecture diagram to a technical document
When writing a technical solution document, a Mermaid flowchart describing the relationship between system components needs to be inserted into it.
Example 3: Standardize company information in contract templates
After the company information changes, the old company name and address in all contract template HWPX files need to be updated.
Frequently Asked Questions
I only have.hwp files and no.hwpx files. Can I use it?
After editing and saving on Mac or Linux, will there be garbled characters or incorrect formatting when opening in Korean office software on Windows?
How does the AI assistant know which tool to call to edit the document?
Will the original file be damaged during the editing process?
Can it be used in other AI tools besides Claude?
Related resources
GitHub project repository
The source code, latest version, and issue tracking of the enhanced HWPX MCP server.
Original project repository
The original project on which this enhanced version is based, for reference.
Model Context Protocol (MCP) official website
Official documentation and specifications for understanding the MCP protocol.
HWPX file format reference
Detailed information about the HWPX (HWP Open XML) format (refer to the relevant documentation of the Korean office software developer).

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
20.3K
4.5 points

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
34.2K
5 points

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
25.4K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.3K
4.3 points

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#
31.0K
5 points

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
64.3K
4.5 points

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
21.0K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
47.4K
4.8 points


