real-estate
Ask Claude about Korean apartment prices — powered by MOLIT's open API
claude mcp add --transport stdio tae0y-real-estate-mcp uv run --directory /path/to/real-estate-mcp python src/real_estate/mcp_server/server.py \ --env DATA_GO_KR_API_KEY="your_api_key_here"
How to use
This MCP server provides access to MOLIT-based Korean real estate data through a collection of 14+ tools. It enables querying apartment trades and rentals, officetel trades and rentals, villa/multi-family housing trades and rentals, single-house trades and rentals, commercial building trades, apartment subscription notices and results, onbid code/address lookups, and regional code lookups. Tools are exposed via the MCP server so you can ask Claude for up-to-date price trends, transaction histories, and listings across property types. Familiar capabilities include get_apartment_trades, get_apartment_rent, get_officetel_trades, get_officetel_rent, get_villa_trades, get_villa_rent, get_single_house_trades, get_single_house_rent, get_commercial_trade, get_apt_subscription_info, get_apt_subscription_results, get_onbid_addr*_info, and get_region_code, among others. To use them, configure the mcpServers entry in Claude Desktop (or your HTTP client) to point at the UV-based server, then issue natural-language prompts or structured requests to retrieve the data you need.
How to install
Prerequisites:
- Install uv (the Universal Viewer) as described in the UV docs.
- Have an API key from the 공공데이터포털 for the required MOLIT data services.
- Have Python source for the MCP server from this repository.
- Clone the repository:
git clone <repository_url>
cd real-estate-mcp
-
Install and set up UV according to the official instructions for your OS.
-
Obtain and export your MOLIT/API key:
export DATA_GO_KR_API_KEY=your_api_key_here
- Run the MCP server via UV (as in the example configuration):
uv run --directory /path/to/real-estate-mcp python src/real_estate/mcp_server/server.py
-
(Optional) Configure Claude Desktop or your client to connect using the provided mcp_config example, replacing the placeholder path with the actual directory where you cloned the project.
-
Verify connectivity by starting Claude Desktop and confirming that the real-estate server appears in the tool list.
Additional notes
Notes and tips:
- Ensure the MOLIT API key has access to all the required data services listed in prerequisites.
- The real-estate MCP supports a wide range of tools; if a specific endpoint returns an error, check that the API key has permission for that service and that the repository data sources are up to date.
- When integrating with Claude Desktop, use the provided JSON snippet under mcpServers to register the server. Adjust the --directory path to the actual repository location.
- If you plan to expose the server via HTTP or other clients, refer to the docs in docs/ for additional setup (e.g., Docker, OAuth).
- Onbid related tools are marked as WIP in the docs; expect partial support for those endpoints.
- Keep your API keys secure and do not commit them to public repositories.
Related MCP Servers
mcpo
A simple, secure MCP-to-OpenAPI proxy server
freecad
FreeCAD MCP(Model Context Protocol) server
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
mcp -aws
A Model Context Protocol server implementation for operations on AWS resources
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
mcp-images
## MCP-Images Looking for a powerful image processing server? MCP Server-Image provides enterprise-grade image handling with just a few lines of code. Perfect for AI applications, web services, and data processing pipelines. [Get Started](#installation) | [Support Us](https://www.buymeacoffee.com/blazzmocompany)