tae0y/real-estate-mcp

🏠 Ask Claude about Korean apartment prices — powered by 국토교통부 open API

What it solves

This project provides a way to connect AI assistants like Claude to live real estate data from South Korea's Ministry of Land, Infrastructure and Transport (MOLIT) API. It allows users to simulate financial scenarios such as buying now, buying later, or investing based on their personal income and retirement goals.

How it works

It implements the Model Context Protocol (MCP), allowing an AI client to call over 14 different tools to fetch real-time transaction data and subscription notices. It connects to various government APIs to retrieve trade and rent information for apartments, officetels, villas, single-houses, and commercial buildings, as well as region code lookups.

Who it’s for

People interested in the South Korean real estate market who want to use an AI assistant to analyze live transaction data and perform financial calculations for property investment or housing goals.

Highlights

  • Over 14 tools for live transaction and rent data across multiple property types.
  • Integration with the MOLIT API for official government data.
  • Support for apartment subscription notices and results.
  • Compatible with Claude Desktop and other MCP-compliant clients via stdio or HTTP.

Related

  • Project
    atilaahmettaner/tradingview-mcp

    A Python‑only server that exposes 39 market‑data, technical‑analysis, screener and back‑testing tools via the Model Context Protocol (MCP). AI assistants (Claude, ChatGPT, Cursor, Copilot, etc.) can call these tools with natural language prompts and receive live data, indicator tables, or interactive charts inside the chat. Self‑hosted for free (MIT license) or available as a hosted SaaS (TradingMCP) for $9 / mo.

  • Project
    zerodha/kite-mcp-server

    An MCP server that gives AI assistants secure access to the Kite Connect trading API for market data retrieval, portfolio management, and trade execution.

  • Project
    hmmhmmhm/daiso-mcp

    Daiso MCP is a publicly hosted MCP server that provides Korean retail (Daiso, GS25, 7‑Eleven, etc.), fuel‑price, location and cinema data as structured API calls. AI agents can connect without any API key, ask natural‑language queries (e.g., “다이소 mcp로 수납박스 검색해줘”), and receive ready‑to‑use JSON results. Optional CLI (`npx daiso`) and Codex Skill (`clawhub install daiso-cli`) give the same functionality locally. Public GET endpoints have a 3 000‑calls‑per‑IP‑per‑day limit; higher usage requires self‑hosting (MIT‑licensed).

  • Project
    micro/mu

    Mu is a self‑hosted runtime for the open‑source **Micro** personal assistant. It offers a web UI, CLI, and HTTP API that let you interact with AI agents through a unified inbox. Agents can call built‑in services (mail, calendar, search, weather, shell, etc.) to fulfill requests. Install with a one‑line script, start the server, create an account, and choose an LLM provider.

  • Project
    tidewave-ai/tidewave_rails

    An MCP server that allows AI coding agents to interact with a running Ruby on Rails application's runtime, database, and logs during development.