chrisryugj/korean-law-mcp

법제처 국가법령정보를 LLM에서 바로 조회하는 MCP 서버. 법령·판례·조례 검색과 인용 검증 | MCP server for Korean law — search statutes, precedents, and ordinances, and verify citations

What it solves

Korean Law MCP addresses the problem of LLM hallucinations in legal contexts by providing a real-time verification layer against the official Ministry of Government Legislation (MOLEG) database. It eliminates the need for users to manually cross-reference laws, precedents, and administrative rules across multiple government portals, while preventing AI from inventing non-existent legal articles.

How it works

It operates as a Model Context Protocol (MCP) server and CLI that connects AI assistants (like Claude, Cursor, or ChatGPT) to 42 official Korean law APIs. The system transforms these APIs into a set of specialized tools that can search for statutes, verify citations, track legislative history, and analyze the impact of law changes. It includes a "hallucination gate" that extracts citations from AI-generated text and cross-checks them against the actual database to mark them as verified, missing, or mismatched.

Who it’s for

  • Legal Professionals & Law Firms: For verifying the current validity of precedents and ensuring citations are accurate.
  • Government Officials: Specifically those managing local ordinances who need to track if higher-level laws have changed.
  • Law Students & Researchers: For conducting comprehensive legal research across statutes, treaties, and interpretations.
  • Corporate Compliance Teams: For monitoring changes in laws related to ISO standards and ESG requirements.

Highlights

  • Citation Verification: Detects fake legal articles and content mismatches between AI output and official law texts.
  • Precedent Citator: A "Shepard's Citator" for Korean law that tracks whether a precedent has been overturned or modified by subsequent rulings.
  • Time Travel & Diff: Automatically retrieves and compares the text of a law from two different dates to show additions, deletions, and changes.
  • Ordinance Radar: Automatically identifies if a local ordinance needs updating based on changes in the superior law.
  • Impact Mapping: Generates Mermaid graphs to visualize how a single legal article influences precedents, constitutional decisions, and other regulations.
  • Action Planning: Converts natural language queries (e.g., "I didn't get my deposit back") into a 5-step legal action plan including diagnosis, remedies, and required documents.

Related

  • Project
    mattt/iMCP

    iMCP is a macOS app (with a bundled `imcp‑server` CLI) that implements the Model Context Protocol, exposing Calendar, Contacts, Location, Maps, Messages, Reminders and Weather as JSON‑LD tools for AI clients like Claude Desktop, Claude Code, Cursor and Amp. Users enable services via macOS permission dialogs, connect the AI client, and then can ask natural‑language questions that the AI fulfills by fetching real personal data locally. The project includes Swift SDK integration, a custom Swift package for reading the iMessage database, and debugging tools (MCP Inspector, Companion).

  • Project
    appium/appium-mcp

    An MCP server that enables AI assistants to automate mobile app testing on iOS and Android using natural language and vision-based element finding.

  • Project
    hmmhmmhm/daiso-mcp

    A Model Context Protocol (MCP) server and CLI tool that connects AI agents to real-time South Korean retail inventory, convenience store data, cinema schedules, and fuel prices.

  • Project
    maquina-app/rails-mcp-server

    A Ruby implementation of the Model Context Protocol (MCP) server that allows LLMs to analyze and interact with Rails projects through structured tools and documentation.

  • Dispatch
    Hugging Face Tiny Agents: Building MCP-Powered Agents in 50 Lines of Code

    Hugging Face demonstrates how to build a functional AI agent using the Model Context Protocol (MCP) and the InferenceClient, reducing the core agent logic to a simple while loop.