A2A-MCP-RealEstate

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.

Category
Visit Server

README

๐Ÿ  A2A MCP Real Estate

Korean Real Estate Recommendation System using FastMCP
AI-powered property analysis with investment value and quality of life evaluation

FastMCP Python FastAPI License

๐Ÿ“‹ Overview

A2A MCP Real Estate๋Š” ํ•œ๊ตญ ๋ถ€๋™์‚ฐ ์‹œ์žฅ์„ ์œ„ํ•œ AI ๊ธฐ๋ฐ˜ ์ถ”์ฒœ ์‹œ์Šคํ…œ์ž…๋‹ˆ๋‹ค. FastMCP(Model Context Protocol) ์„œ๋ฒ„๋ฅผ ํ†ตํ•ด ๋ถ€๋™์‚ฐ ์‹ค๊ฑฐ๋ž˜๊ฐ€ ๋ฐ์ดํ„ฐ ๋ถ„์„, ์œ„์น˜ ๊ธฐ๋ฐ˜ ์„œ๋น„์Šค, ๊ทธ๋ฆฌ๊ณ  ํˆฌ์ž๊ฐ€์น˜์™€ ์‚ถ์˜์งˆ์„ ์ข…ํ•ฉํ•œ ๋งž์ถคํ˜• ๋ถ€๋™์‚ฐ ์ถ”์ฒœ ์„œ๋น„์Šค๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.

โœจ Key Features

  • ๐Ÿข ์‹ค๊ฑฐ๋ž˜๊ฐ€ ๋ฐ์ดํ„ฐ ์กฐํšŒ: ๊ตญํ† ๊ตํ†ต๋ถ€ ๊ณต๊ณต๋ฐ์ดํ„ฐ API ์—ฐ๋™
  • ๐Ÿ“ ์œ„์น˜ ๊ธฐ๋ฐ˜ ๋ถ„์„: ์ง€ํ•˜์ฒ ์—ญ ๊ฑฐ๋ฆฌ, ํŽธ์˜์‹œ์„ค, ๊ณต์› ์ ‘๊ทผ์„ฑ ๋ถ„์„
  • ๐Ÿ’ฐ ํˆฌ์ž๊ฐ€์น˜ ํ‰๊ฐ€: AI ๊ธฐ๋ฐ˜ ํˆฌ์ž ์ˆ˜์ต์„ฑ ๋ถ„์„
  • ๐ŸŒฟ ์‚ถ์˜์งˆ ํ‰๊ฐ€: ๊ฑฐ์ฃผ ํ™˜๊ฒฝ์˜ ํŽธ์˜์„ฑ๊ณผ ์•ˆ์ „์„ฑ ๋ถ„์„
  • ๐ŸŽฏ ๋งž์ถคํ˜• ์ถ”์ฒœ: ์‚ฌ์šฉ์ž ์„ฑํ–ฅ๋ณ„ ๋ถ€๋™์‚ฐ ์ถ”์ฒœ (ํˆฌ์ž/์‚ถ์˜์งˆ/๊ท ํ˜•)
  • ๐ŸŒ ์›น ์ธํ„ฐํŽ˜์ด์Šค: ์ง๊ด€์ ์ธ ๋ถ€๋™์‚ฐ ๋ถ„์„ ๋„๊ตฌ

๐Ÿš€ Quick Start

Prerequisites

  • Python 3.12+
  • ๊ตญํ† ๊ตํ†ต๋ถ€ ๊ณต๊ณต๋ฐ์ดํ„ฐํฌํ„ธ API ํ‚ค
  • ๋„ค์ด๋ฒ„ ํด๋ผ์šฐ๋“œ ํ”Œ๋žซํผ 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"
    }
  }
}

๐Ÿ› ๏ธ MCP Tools

Real Estate Recommendation Server

Tool Name Description Parameters
get_real_estate_data ๋ถ€๋™์‚ฐ ์‹ค๊ฑฐ๋ž˜๊ฐ€ ์กฐํšŒ lawd_cd, deal_ymd, property_type
analyze_location ์œ„์น˜ ๋ถ„์„ (์ง€ํ•˜์ฒ , ํŽธ์˜์‹œ์„ค) address, lat, lon
evaluate_investment_value ํˆฌ์ž๊ฐ€์น˜ ํ‰๊ฐ€ Property details + preferences
evaluate_life_quality ์‚ถ์˜์งˆ๊ฐ€์น˜ ํ‰๊ฐ€ Property details + preferences
recommend_property ์ข…ํ•ฉ ๋ถ€๋™์‚ฐ ์ถ”์ฒœ All property details + user_preference

Location Service Server

Tool Name Description Parameters
find_nearest_subway_stations ๊ฐ€์žฅ ๊ฐ€๊นŒ์šด ์ง€ํ•˜์ฒ ์—ญ ๊ฒ€์ƒ‰ address, lat, lon, limit
address_to_coordinates ์ฃผ์†Œ๋ฅผ ์ขŒํ‘œ๋กœ ๋ณ€ํ™˜ address
find_nearby_facilities ์ฃผ๋ณ€ ํŽธ์˜์‹œ์„ค ๊ฒ€์ƒ‰ lat, lon, category, radius
calculate_location_score ์œ„์น˜ ์ ์ˆ˜ ๊ณ„์‚ฐ subway_distance, facilities_count, park_distance

๐Ÿ“Š Evaluation System

Investment Value Analysis (ํˆฌ์ž๊ฐ€์น˜ ํ‰๊ฐ€)

Factor Weight Description
๐Ÿท๏ธ Price 25% ์‹œ์„ธ ๋Œ€๋น„ ๊ฐ€๊ฒฉ ํ•ฉ๋ฆฌ์„ฑ
๐Ÿ“ Area 20% ํˆฌ์ž ์„ ํ˜ธ ๋ฉด์ ๋Œ€ (20-35ํ‰)
๐Ÿข Floor 15% ์ค‘๊ฐ„์ธต~์ค‘์ƒ์ธต ์„ ํ˜ธ๋„
๐Ÿš‡ Transportation 25% ์ง€ํ•˜์ฒ  ์ ‘๊ทผ์„ฑ
๐Ÿ”ฎ Future Value 15% ์žฌ๊ฑด์ถ•/๊ฐœ๋ฐœ ๊ฐ€๋Šฅ์„ฑ

Quality of Life Analysis (์‚ถ์˜์งˆ๊ฐ€์น˜ ํ‰๊ฐ€)

Factor Weight Description
๐ŸŒณ Environment 25% ๊ณต์›, ๋…น์ง€ ์ ‘๊ทผ์„ฑ
๐Ÿช Convenience 25% ํŽธ์˜์‹œ์„ค ๊ฐœ์ˆ˜ ๋ฐ ์ ‘๊ทผ์„ฑ
๐Ÿ›ก๏ธ Safety 20% ์ธต์ˆ˜, ์น˜์•ˆ, ๊ตํ†ต์•ˆ์ „
๐ŸŽ“ Education 15% ํ•™๊ต, ํ•™์›๊ฐ€ ์ ‘๊ทผ์„ฑ
๐ŸŽญ Culture 15% ๋ฌธํ™”์‹œ์„ค ์ ‘๊ทผ์„ฑ

Grading System

  • A+ (90-100์ ): ๋งค์šฐ ์šฐ์ˆ˜ - ๊ฐ•๋ ฅ ์ถ”์ฒœ
  • A (80-89์ ): ์šฐ์ˆ˜ - ์ถ”์ฒœ
  • B+ (70-79์ ): ์–‘ํ˜ธ - ์กฐ๊ฑด๋ถ€ ์ถ”์ฒœ
  • B (60-69์ ): ๋ณดํ†ต - ์‹ ์ค‘ ๊ฒ€ํ† 
  • C (60์  ๋ฏธ๋งŒ): ๊ฐœ์„  ํ•„์š” - ๋ณด๋ฅ˜

๐Ÿ—๏ธ Architecture

๐Ÿ“ A2A-MCP-RealEstate/
โ”œโ”€โ”€ ๐Ÿ“‚ app/
โ”‚   โ”œโ”€โ”€ ๐Ÿ“‚ mcp/                    # FastMCP Servers
โ”‚   โ”‚   โ”œโ”€โ”€ ๐Ÿ  real_estate_recommendation_mcp.py  # Main recommendation server
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“ location_service.py                # Location analysis server
โ”‚   โ”œโ”€โ”€ ๐Ÿ“‚ routes/                 # Web API Routes
โ”‚   โ”‚   โ”œโ”€โ”€ ๐ŸŒ web_routes.py       # Web interface routes
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ”ง mcp_routes.py       # MCP API routes
โ”‚   โ”œโ”€โ”€ ๐Ÿ“‚ utils/                  # Utilities
โ”‚   โ”‚   โ”œโ”€โ”€ ๐Ÿ”Œ mcp_client.py       # MCP client utilities
โ”‚   โ”‚   โ”œโ”€โ”€ โš™๏ธ config.py           # Configuration management
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“ logger.py           # Logging utilities
โ”‚   โ”œโ”€โ”€ ๐Ÿ“‚ templates/              # HTML Templates
โ”‚   โ”‚   โ”œโ”€โ”€ ๐Ÿ  index.html          # Home page
โ”‚   โ”‚   โ”œโ”€โ”€ ๐Ÿงช mcp_test.html       # MCP testing interface
โ”‚   โ”‚   โ”œโ”€โ”€ ๐Ÿค– agent_test.html     # Agent testing interface
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“Š result templates    # Result display templates
โ”‚   โ””โ”€โ”€ ๐Ÿ“„ main.py                 # FastAPI application
โ”œโ”€โ”€ ๐Ÿ“„ runner.py                   # Application runner
โ”œโ”€โ”€ ๐Ÿ“„ requirements.txt            # Python dependencies
โ”œโ”€โ”€ ๐Ÿ“„ task.md                     # Development tasks
โ””โ”€โ”€ ๐Ÿ“„ README.md                   # This file

๐Ÿ“ฑ Web Interface

Home Page

  • ์‹œ์Šคํ…œ ๊ฐœ์š” ๋ฐ ์ฃผ์š” ๊ธฐ๋Šฅ ์†Œ๊ฐœ
  • MCP ํ…Œ์ŠคํŠธ์™€ Agent ํ…Œ์ŠคํŠธ๋กœ์˜ ์ง์ ‘ ๋งํฌ

MCP Testing Interface

  • ์‹ค๊ฑฐ๋ž˜๊ฐ€ ์กฐํšŒ ๋„๊ตฌ ํ…Œ์ŠคํŠธ
  • ์ง€ํ•˜์ฒ ์—ญ ๊ฒ€์ƒ‰ ๋„๊ตฌ ํ…Œ์ŠคํŠธ
  • ํŽธ์˜์‹œ์„ค ๊ฒ€์ƒ‰ ๋„๊ตฌ ํ…Œ์ŠคํŠธ
  • ์œ„์น˜ ์ ์ˆ˜ ๊ณ„์‚ฐ ๋„๊ตฌ ํ…Œ์ŠคํŠธ

Agent Testing Interface

  • ๋ถ€๋™์‚ฐ ์ •๋ณด ์ž…๋ ฅ ํผ
  • ์‹ค์‹œ๊ฐ„ ํˆฌ์ž๊ฐ€์น˜ ๋ฐ ์‚ถ์˜์งˆ ๋ถ„์„
  • ์ข…ํ•ฉ ์ถ”์ฒœ ๊ฒฐ๊ณผ ์‹œ๊ฐํ™”
  • ์ƒ์„ธ ํ‰๊ฐ€ ๋ฆฌํฌํŠธ

๐Ÿ”ง API Keys Setup

1. ๊ตญํ† ๊ตํ†ต๋ถ€ ๊ณต๊ณต๋ฐ์ดํ„ฐํฌํ„ธ

  1. ๊ณต๊ณต๋ฐ์ดํ„ฐํฌํ„ธ ํšŒ์›๊ฐ€์ž…
  2. "์•„ํŒŒํŠธ ์‹ค๊ฑฐ๋ž˜๊ฐ€ ์ •๋ณด" ํ™œ์šฉ์‹ ์ฒญ
  3. ์Šน์ธ๋œ API ํ‚ค๋ฅผ MOLIT_API_KEY์— ์„ค์ •

2. ๋„ค์ด๋ฒ„ ํด๋ผ์šฐ๋“œ ํ”Œ๋žซํผ

  1. ๋„ค์ด๋ฒ„ ํด๋ผ์šฐ๋“œ ํ”Œ๋žซํผ ํ”„๋กœ์ ํŠธ ์ƒ์„ฑ
  2. "Application > Maps" ์„œ๋น„์Šค ์‹ ์ฒญ
  3. ํด๋ผ์ด์–ธํŠธ ID๋ฅผ NAVER_CLIENT_ID์— ์„ค์ •
  4. ํด๋ผ์ด์–ธํŠธ ์‹œํฌ๋ฆฟ์„ NAVER_CLIENT_SECRET์— ์„ค์ •

๐Ÿ“ˆ 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 ํ…Œ์ŠคํŠธ" for data query testing
# 2. Go to "Agent ํ…Œ์ŠคํŠธ" 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": "์•„ํŒŒํŠธ"
    }
})

๐Ÿค Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

๐Ÿ“ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ™ Acknowledgments

  • FastMCP: FastMCP framework for rapid MCP server development
  • ๊ตญํ† ๊ตํ†ต๋ถ€: Real estate transaction data via public data portal
  • ์นด์นด์˜ค: Location and mapping services
  • FastAPI: Modern web framework for building APIs
  • Bootstrap: Frontend framework for responsive web design

๐Ÿ“ž Support


๐Ÿ  A2A MCP Real Estate - Making Korean real estate investment decisions smarter with AI and MCP technology.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured