
Real Estate MCP Server
Enables real estate property searches with location and criteria filtering, plus comprehensive mortgage calculations including monthly payments and affordability analysis. Currently uses mock data for property searches but provides full mortgage calculation functionality.
README
Real Estate MCP Server
A Model Context Protocol (MCP) server that provides real estate search and mortgage calculation tools.
Features
Available Tools
-
property.search - Search for properties with filters
- Location-based search
- Price range filtering
- Bedrooms/bathrooms filtering
- Square footage filtering
- Property type filtering
- Note: Currently returns mock data - real API integration needed
-
mortgage.calculate - Calculate monthly mortgage payments
- Principal & interest calculation
- Property tax breakdown
- Insurance costs
- HOA fees
- PMI estimation
-
mortgage.affordability - Calculate home affordability
- Estimate maximum home price based on monthly payment budget
- Considers down payment and loan terms
Installation
Prerequisites
- Node.js 18+ (check with
node --version
) - npm or yarn
Install from Source
# Clone the repository
git clone https://github.com/klappe-pm/Real-Estate-MCP.git
cd Real-Estate-MCP
# Install dependencies
npm install
# Build the TypeScript code
npm run build
Development Mode
# Run in watch mode for development
npm run dev
Usage with Claude Desktop
Configure Claude Desktop
- Edit your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
- Add the server configuration:
{
"mcpServers": {
"real-estate": {
"command": "node",
"args": ["/path/to/Real-Estate-MCP/dist/index.js"],
"env": {}
}
}
}
Replace /path/to/Real-Estate-MCP
with the actual path to your cloned repository.
- Restart Claude Desktop
Using with npx (No Installation)
You can also run directly without cloning:
{
"mcpServers": {
"real-estate": {
"command": "npx",
"args": ["-y", "real-estate-mcp"]
}
}
}
Note: This requires publishing to npm first.
Example Usage in Claude
Once configured, you can use the tools in Claude:
"Search for homes in Austin, Texas under $600,000 with at least 3 bedrooms"
"Calculate the monthly mortgage payment for a $500,000 home with 20% down,
6.5% interest rate, 30-year term, $6000/year property tax, and $1200/year insurance"
"What's the maximum home price I can afford with a $3000/month budget,
$100,000 down payment, and 6.5% interest rate?"
API Integration
The property search currently returns mock data. To integrate real APIs:
Zillow Integration
- Use RapidAPI's Zillow endpoints (unofficial)
- Or implement web scraping (check ToS and robots.txt)
- Store API key in environment variables
Redfin Integration
- No official public API available
- Consider unofficial endpoints or web scraping
- Respect rate limits and ToS
MLS Integration
- Requires MLS membership or broker partnership
- Different APIs per region (RETS, Web API, etc.)
- Authentication typically required
Alternative APIs
- Rentberry API
- Realty Mole API
- RentSpree API
- Estated API
Development
Project Structure
src/
├── index.ts # Main MCP server
├── tools/
│ ├── property-search.ts # Property search implementation
│ └── mortgage-calculator.ts # Mortgage calculations
└── types/
└── real-estate.ts # TypeScript interfaces
Available Scripts
npm run dev
- Start development server with hot reloadnpm run build
- Build TypeScript to JavaScriptnpm run lint
- Run ESLintnpm run type-check
- Check TypeScript types
Adding New Tools
- Create a new tool file in
src/tools/
- Define the tool's input/output types in
src/types/
- Register the tool in
src/index.ts
usingserver.tool()
- Rebuild with
npm run build
Environment Variables
For production API integration, set these environment variables:
ZILLOW_API_KEY=your_api_key
REDFIN_API_KEY=your_api_key
MLS_API_KEY=your_api_key
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Run tests and linting
- Submit a pull request
License
MIT - See LICENSE file for details
Support
For issues and questions:
- GitHub Issues: https://github.com/klappe-pm/Real-Estate-MCP/issues
Roadmap
- [ ] Integrate real Zillow API
- [ ] Add Redfin data source
- [ ] MLS integration
- [ ] Add rental property search
- [ ] Investment property analysis tools
- [ ] Comparative market analysis (CMA)
- [ ] Property valuation estimates
- [ ] Neighborhood data integration
- [ ] School district information
- [ ] Crime statistics
- [ ] Walk/transit scores
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.