Kordoc
An MCP server that parses South Korean document formats like HWP, HWPX, and PDF into Markdown. It features specialized table reconstruction and security-hardened extraction optimized for administrative and public institution files.
What is Kordoc?
Kordoc is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that parses south korean document formats like hwp, hwpx, and pdf into markdown. it features specialized table reconstruction and security-hardened extraction optimized for administrative a...
An MCP server that parses South Korean document formats like HWP, HWPX, and PDF into Markdown. It features specialized table reconstruction and security-hardened extraction optimized for administrative and public institution files.
This server falls under the File Systems and Search & Data Extraction categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that parses South Korean document formats like
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx kordocConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Kordoc
Kordoc is an MCP server that parses South Korean document formats — HWP, HWPX, HWPML, PDF, DOCX, and XLSX — into clean Markdown, making their contents accessible to AI assistants that cannot natively read these formats. It provides eight tools covering full document parsing, table extraction, form field reading and filling, document comparison, and page-range extraction, with specialized handling for the complex merged-table structures common in Korean government and administrative files. Researchers, government contractors, and Korean enterprise teams use it to feed Hancom Office and PDF documents into AI workflows for summarization, translation, and data extraction.
Prerequisites
- Node.js 18+ installed (kordoc is distributed as an npm package via npx)
- An MCP-compatible client such as Claude Desktop, Cursor, Claude Code CLI, or Windsurf
- HWP/HWPX files available on your local filesystem for parsing
- No additional API keys required
Run the setup wizard
The interactive setup wizard automatically detects installed AI clients and patches their MCP configuration files. This is the recommended approach and avoids manual JSON editing.
npx -y kordoc setupVerify the configuration was applied
The wizard modifies your client config files automatically. On macOS/Linux it patches the JSON directly; on Windows it wraps commands with cmd /c npx. Restart your AI client after setup completes.
Manual configuration (alternative)
If you prefer manual setup, add kordoc to your claude_desktop_config.json directly.
{
"mcpServers": {
"kordoc": {
"command": "npx",
"args": ["-y", "kordoc"]
}
}
}Test with a CLI parse (no setup needed)
You can also use kordoc as a standalone CLI tool to convert a single file to Markdown without any client setup.
npx kordoc 보고서.hwpxParse documents through your AI client
Once configured, point your AI client to an HWP, PDF, or DOCX file and ask it to extract or summarize the content. Kordoc's parse_document tool will convert it to Markdown on the fly.
Kordoc Examples
Client configuration
Claude Desktop config block for running kordoc via npx.
{
"mcpServers": {
"kordoc": {
"command": "npx",
"args": ["-y", "kordoc"]
}
}
}Prompts to try
Example prompts for parsing, comparing, and extracting data from Korean document formats.
- "Parse this HWPX file and give me a summary: /Users/me/docs/보고서.hwpx"
- "Extract all tables from 계약서.pdf"
- "Compare these two versions of the document and show what changed"
- "Fill in the application form 신청서.hwpx with the following values: 성명=홍길동, 주소=서울"
- "Extract only pages 3 through 7 from 안내문.pdf"Troubleshooting Kordoc
HWP files fail to parse with an encoding error
Older HWP 3.x files use a different binary format than HWP 5.x and HWPX. Confirm the file version using the detect_format tool first. Kordoc supports HWP 5.x natively; very old 3.x files may require conversion to HWPX first using Hancom Office.
Tables are missing or malformed in the Markdown output
Use the parse_table tool with a specific table index rather than relying on full document parse for complex merged tables. Kordoc detects merged cells and provides a fallback HTML representation when Markdown cannot accurately represent the structure.
npx kordoc setup does not detect my AI client
The wizard searches standard installation paths. If your client is installed in a non-standard location, use the manual configuration method and add the kordoc server entry to your client's MCP config file directly.
Frequently Asked Questions about Kordoc
What is Kordoc?
Kordoc is a Model Context Protocol (MCP) server that mcp server that parses south korean document formats like hwp, hwpx, and pdf into markdown. it features specialized table reconstruction and security-hardened extraction optimized for administrative and public institution files. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Kordoc?
Follow the installation instructions on the Kordoc GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Kordoc?
Kordoc works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Kordoc free to use?
Yes, Kordoc is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Kordoc Alternatives — Similar File Systems Servers
Looking for alternatives to Kordoc? Here are other popular file systems servers you can use with Claude, Cursor, and VS Code.
Electerm
★ 14.1k📻Terminal/ssh/sftp/ftp/telnet/serialport/RDP/VNC/Spice client(linux, mac, win)
Plik
★ 1.8kPlik is a temporary file upload system (Wetransfer like) in Go.
macOS Automator
★ 801A Model Context Protocol server that enables execution of AppleScript and JavaScript for Automation scripts on macOS, allowing programmatic control of applications and system functions through a rich knowledge base of pre-defined scripts.
PDF Reader
★ 723Enables reading, searching, and metadata extraction from PDF files without loading the entire content into the context window. It provides efficient tools for text cleaning, page-specific extraction, and context-aware search results.
Filesystem MCP Server
★ 643Provides comprehensive filesystem operations (read, write, list, create, delete, move files and directories) through the Model Context Protocol with Streamable HTTP transport and built-in security through configurable root directory restrictions.
Ebook
★ 366A lightweight MCP server that allows LLMs to read and interact with your personal PDF and EPUB ebooks on your local machine. Ideal for building AI reading assistants or chat-based ebook interfaces.
Browse More File Systems MCP Servers
Explore all file systems servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Kordoc in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Kordoc?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.