A2A-MCP-RealEstate
AI-powered Korean real estate analysis and recommendation system providing property data, location analysis, and combined investment and quality of life evaluation.
README
๐ A2A MCP Real Estate
Korean Real Estate Recommendation System using FastMCP
AI-powered property analysis with investment value and quality of life evaluation
๐ Overview
A2A MCP Real Estate๋ ํ๊ตญ ๋ถ๋์ฐ ์์ฅ์ ์ํ AI ๊ธฐ๋ฐ ์ถ์ฒ ์์คํ ์ ๋๋ค. FastMCP(Model Context Protocol) ์๋ฒ๋ฅผ ํตํด ๋ถ๋์ฐ ์ค๊ฑฐ๋๊ฐ ๋ฐ์ดํฐ ๋ถ์, ์์น ๊ธฐ๋ฐ ์๋น์ค, ๊ทธ๋ฆฌ๊ณ ํฌ์๊ฐ์น์ ์ถ์์ง์ ์ข ํฉํ ๋ง์ถคํ ๋ถ๋์ฐ ์ถ์ฒ ์๋น์ค๋ฅผ ์ ๊ณตํฉ๋๋ค.
โจ Key Features
- ๐ข ์ค๊ฑฐ๋๊ฐ ๋ฐ์ดํฐ ์กฐํ: ๊ตญํ ๊ตํต๋ถ ๊ณต๊ณต๋ฐ์ดํฐ API ์ฐ๋
- ๐ ์์น ๊ธฐ๋ฐ ๋ถ์: ์งํ์ฒ ์ญ ๊ฑฐ๋ฆฌ, ํธ์์์ค, ๊ณต์ ์ ๊ทผ์ฑ ๋ถ์
- ๐ฐ ํฌ์๊ฐ์น ํ๊ฐ: AI ๊ธฐ๋ฐ ํฌ์ ์์ต์ฑ ๋ถ์
- ๐ฟ ์ถ์์ง ํ๊ฐ: ๊ฑฐ์ฃผ ํ๊ฒฝ์ ํธ์์ฑ๊ณผ ์์ ์ฑ ๋ถ์
- ๐ฏ ๋ง์ถคํ ์ถ์ฒ: ์ฌ์ฉ์ ์ฑํฅ๋ณ ๋ถ๋์ฐ ์ถ์ฒ (ํฌ์/์ถ์์ง/๊ท ํ)
- ๐ ์น ์ธํฐํ์ด์ค: ์ง๊ด์ ์ธ ๋ถ๋์ฐ ๋ถ์ ๋๊ตฌ
๐ Quick Start
Prerequisites
- Python 3.12+
- ๊ตญํ ๊ตํต๋ถ ๊ณต๊ณต๋ฐ์ดํฐํฌํธ API ํค
- ๋ค์ด๋ฒ ํด๋ผ์ฐ๋ ํ๋ซํผ API ํค
Installation
# Clone the repository
git clone https://github.com/your-username/A2A-MCP-RealEstate.git
cd A2A-MCP-RealEstate
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\\Scripts\\activate
# Install dependencies
pip install -r requirements.txt
# Set up environment variables
cp .env.example .env
# Edit .env file with your API keys
Environment Variables
# .env file
MOLIT_API_KEY=your_molit_api_key_here
NAVER_CLIENT_ID=your_naver_client_id_here
NAVER_CLIENT_SECRET=your_naver_client_secret_here
PORT=8080
AGENT_ID=agent-py-001
AGENT_NAME=A2A_Python_Agent
LOG_LEVEL=INFO
ENVIRONMENT=development
Running the Application
1. Web Interface (Recommended)
# Start the web server
python runner.py
# Access the web interface
open http://localhost:8080/web/
2. MCP Servers (Standalone)
# Real Estate Recommendation MCP Server
python app/mcp/real_estate_recommendation_mcp.py
# Location Service MCP Server
python app/mcp/location_service.py
3. Claude Desktop Integration
Add to your Claude Desktop MCP configuration:
{
"mcpServers": {
"korean-realestate": {
"command": "python",
"args": ["app/mcp/real_estate_recommendation_mcp.py"],
"cwd": "/path/to/A2A-MCP-RealEstate"
}
}
}
๐ ๏ธ MCP Tools
Real Estate Recommendation Server
| Tool Name | Description | Parameters |
|---|---|---|
get_real_estate_data |
๋ถ๋์ฐ ์ค๊ฑฐ๋๊ฐ ์กฐํ | lawd_cd, deal_ymd, property_type |
analyze_location |
์์น ๋ถ์ (์งํ์ฒ , ํธ์์์ค) | address, lat, lon |
evaluate_investment_value |
ํฌ์๊ฐ์น ํ๊ฐ | Property details + preferences |
evaluate_life_quality |
์ถ์์ง๊ฐ์น ํ๊ฐ | Property details + preferences |
recommend_property |
์ข ํฉ ๋ถ๋์ฐ ์ถ์ฒ | All property details + user_preference |
Location Service Server
| Tool Name | Description | Parameters |
|---|---|---|
find_nearest_subway_stations |
๊ฐ์ฅ ๊ฐ๊น์ด ์งํ์ฒ ์ญ ๊ฒ์ | address, lat, lon, limit |
address_to_coordinates |
์ฃผ์๋ฅผ ์ขํ๋ก ๋ณํ | address |
find_nearby_facilities |
์ฃผ๋ณ ํธ์์์ค ๊ฒ์ | lat, lon, category, radius |
calculate_location_score |
์์น ์ ์ ๊ณ์ฐ | subway_distance, facilities_count, park_distance |
๐ Evaluation System
Investment Value Analysis (ํฌ์๊ฐ์น ํ๊ฐ)
| Factor | Weight | Description |
|---|---|---|
| ๐ท๏ธ Price | 25% | ์์ธ ๋๋น ๊ฐ๊ฒฉ ํฉ๋ฆฌ์ฑ |
| ๐ Area | 20% | ํฌ์ ์ ํธ ๋ฉด์ ๋ (20-35ํ) |
| ๐ข Floor | 15% | ์ค๊ฐ์ธต~์ค์์ธต ์ ํธ๋ |
| ๐ Transportation | 25% | ์งํ์ฒ ์ ๊ทผ์ฑ |
| ๐ฎ Future Value | 15% | ์ฌ๊ฑด์ถ/๊ฐ๋ฐ ๊ฐ๋ฅ์ฑ |
Quality of Life Analysis (์ถ์์ง๊ฐ์น ํ๊ฐ)
| Factor | Weight | Description |
|---|---|---|
| ๐ณ Environment | 25% | ๊ณต์, ๋ น์ง ์ ๊ทผ์ฑ |
| ๐ช Convenience | 25% | ํธ์์์ค ๊ฐ์ ๋ฐ ์ ๊ทผ์ฑ |
| ๐ก๏ธ Safety | 20% | ์ธต์, ์น์, ๊ตํต์์ |
| ๐ Education | 15% | ํ๊ต, ํ์๊ฐ ์ ๊ทผ์ฑ |
| ๐ญ Culture | 15% | ๋ฌธํ์์ค ์ ๊ทผ์ฑ |
Grading System
- A+ (90-100์ ): ๋งค์ฐ ์ฐ์ - ๊ฐ๋ ฅ ์ถ์ฒ
- A (80-89์ ): ์ฐ์ - ์ถ์ฒ
- B+ (70-79์ ): ์ํธ - ์กฐ๊ฑด๋ถ ์ถ์ฒ
- B (60-69์ ): ๋ณดํต - ์ ์ค ๊ฒํ
- C (60์ ๋ฏธ๋ง): ๊ฐ์ ํ์ - ๋ณด๋ฅ
๐๏ธ Architecture
๐ A2A-MCP-RealEstate/
โโโ ๐ app/
โ โโโ ๐ mcp/ # FastMCP Servers
โ โ โโโ ๐ real_estate_recommendation_mcp.py # Main recommendation server
โ โ โโโ ๐ location_service.py # Location analysis server
โ โโโ ๐ routes/ # Web API Routes
โ โ โโโ ๐ web_routes.py # Web interface routes
โ โ โโโ ๐ง mcp_routes.py # MCP API routes
โ โโโ ๐ utils/ # Utilities
โ โ โโโ ๐ mcp_client.py # MCP client utilities
โ โ โโโ โ๏ธ config.py # Configuration management
โ โ โโโ ๐ logger.py # Logging utilities
โ โโโ ๐ templates/ # HTML Templates
โ โ โโโ ๐ index.html # Home page
โ โ โโโ ๐งช mcp_test.html # MCP testing interface
โ โ โโโ ๐ค agent_test.html # Agent testing interface
โ โ โโโ ๐ result templates # Result display templates
โ โโโ ๐ main.py # FastAPI application
โโโ ๐ runner.py # Application runner
โโโ ๐ requirements.txt # Python dependencies
โโโ ๐ task.md # Development tasks
โโโ ๐ README.md # This file
๐ฑ Web Interface
Home Page
- ์์คํ ๊ฐ์ ๋ฐ ์ฃผ์ ๊ธฐ๋ฅ ์๊ฐ
- MCP ํ ์คํธ์ Agent ํ ์คํธ๋ก์ ์ง์ ๋งํฌ
MCP Testing Interface
- ์ค๊ฑฐ๋๊ฐ ์กฐํ ๋๊ตฌ ํ ์คํธ
- ์งํ์ฒ ์ญ ๊ฒ์ ๋๊ตฌ ํ ์คํธ
- ํธ์์์ค ๊ฒ์ ๋๊ตฌ ํ ์คํธ
- ์์น ์ ์ ๊ณ์ฐ ๋๊ตฌ ํ ์คํธ
Agent Testing Interface
- ๋ถ๋์ฐ ์ ๋ณด ์ ๋ ฅ ํผ
- ์ค์๊ฐ ํฌ์๊ฐ์น ๋ฐ ์ถ์์ง ๋ถ์
- ์ข ํฉ ์ถ์ฒ ๊ฒฐ๊ณผ ์๊ฐํ
- ์์ธ ํ๊ฐ ๋ฆฌํฌํธ
๐ง API Keys Setup
1. ๊ตญํ ๊ตํต๋ถ ๊ณต๊ณต๋ฐ์ดํฐํฌํธ
- ๊ณต๊ณต๋ฐ์ดํฐํฌํธ ํ์๊ฐ์
- "์ํํธ ์ค๊ฑฐ๋๊ฐ ์ ๋ณด" ํ์ฉ์ ์ฒญ
- ์น์ธ๋ API ํค๋ฅผ
MOLIT_API_KEY์ ์ค์
2. ๋ค์ด๋ฒ ํด๋ผ์ฐ๋ ํ๋ซํผ
- ๋ค์ด๋ฒ ํด๋ผ์ฐ๋ ํ๋ซํผ ํ๋ก์ ํธ ์์ฑ
- "Application > Maps" ์๋น์ค ์ ์ฒญ
- ํด๋ผ์ด์ธํธ ID๋ฅผ
NAVER_CLIENT_ID์ ์ค์ - ํด๋ผ์ด์ธํธ ์ํฌ๋ฆฟ์
NAVER_CLIENT_SECRET์ ์ค์
๐ Usage Examples
CLI Example (MCP Server)
# Start the MCP server
python app/mcp/real_estate_recommendation_mcp.py
# The server will be available for MCP clients
# Example tools: get_real_estate_data, recommend_property, etc.
Web Interface Example
# Start web server
python runner.py
# Navigate to http://localhost:8080/web/
# 1. Go to "MCP ํ
์คํธ" for data query testing
# 2. Go to "Agent ํ
์คํธ" for property recommendation
API Example
import httpx
# Get apartment trade data
response = await httpx.post("http://localhost:8080/web/api/mcp/test", json={
"tool_name": "get_real_estate_data",
"parameters": {
"lawd_cd": "11680", # Gangnam-gu, Seoul
"deal_ymd": "202401", # January 2024
"property_type": "์ํํธ"
}
})
๐ค Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Acknowledgments
- FastMCP: FastMCP framework for rapid MCP server development
- ๊ตญํ ๊ตํต๋ถ: Real estate transaction data via public data portal
- ์นด์นด์ค: Location and mapping services
- FastAPI: Modern web framework for building APIs
- Bootstrap: Frontend framework for responsive web design
๐ Support
- ๐ง Issues: GitHub Issues
- ๐ Documentation: See
/docsendpoint when running the server - ๐ฌ Discussions: GitHub Discussions
๐ A2A MCP Real Estate - Making Korean real estate investment decisions smarter with AI and MCP technology.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.