mcp vs hwp-mcp
mcp: This MCP server uses pre-computed code graphs to provide sub-second responses for symbol lookups, call-graph traversal, and cross-subsystem analysis. It integrates with AI agents via the Model Context Protocol, offering both default symbol context mode and experimental GraphRAG mode for deeper code exploration. The server supports caching for fast performance and works with popular MCP clients like Claude Code CLI and Cursor.; hwp-mcp: hwp-mcp is an MCP server for reading and writing Korean Hangul (.hwp / .hwpx) documents from Claude, Cursor, ChatGPT and any MCP-compatible client. It supports reading both .hwp and .hwpx formats, and writing (find/replace, template filling, new document creation) for .hwpx. Built on top of the rhwp engine, it provides 34 MCP tools for text manipulation, table editing, image handling, rendering, and document creation.
TL;DR
AI agents understanding unfamiliar codebases instantly
Automate reading and extracting content from Korean government or business Hangul documents
Side-by-Side Comparison
Features
Use Cases
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.