Rentcast MCP Server
Enables intelligent property data analysis through the Rentcast API with optimized API call allocation. Provides comprehensive real estate market insights, property valuations, rental estimates, and listings data with built-in rate limiting and fallback mechanisms.
README
🏠 Rentcast MCP Server
A Model Context Protocol (MCP) server that provides access to Rentcast Real Estate API data through a standardized interface. This server enables AI assistants and applications to retrieve comprehensive real estate information including property details, market analysis, rent estimates, and property valuations.
✨ Features
- 🔍 Property Search: Search properties with filters (city, state, bedrooms, bathrooms, etc.)
- 🎲 Random Properties: Get random properties for market analysis
- 📊 Market Analysis: Comprehensive market statistics and trends
- 💰 Property Valuation: Automated property value estimates with comparables
- 🏠 Rent Estimates: Long-term rent estimates with comparable properties
- 🏘️ Sale Listings: Current properties for sale
- 🏘️ Rental Listings: Current properties for rent
- 🏠 Property Details: Detailed property information and parameters
🚀 Quick Start
Prerequisites
- Node.js 18+
- Rentcast API key (Get one here)
Installation
# Clone the repository
git clone https://github.com/tandat8503/mcp_rentcast.git
cd mcp_rentcast
# Install dependencies
npm install
# Copy environment file
cp .env.example .env
# Edit .env with your Rentcast API key
RENTCAST_API_KEY=your_api_key_here
# Build the project
npm run build
# Start the server
npm start
Using with MCP Inspector
# Start MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js
# Open browser at http://localhost:6274
# Use the provided auth token to access the interface
🛠️ Available Tools
1. search_properties
Search for properties with comprehensive information.
Parameters:
city(optional): City name (e.g., "Austin", "New York")state(optional): State abbreviation (e.g., "TX", "CA")zipCode(optional): ZIP code (e.g., "78705")bedrooms(optional): Number of bedrooms (1-10)bathrooms(optional): Number of bathrooms (1-10)propertyType(optional): Property type (e.g., "Single Family", "Condo")limit(optional): Maximum results (default: 15, max: 50)
Example:
{
"city": "Austin",
"state": "TX",
"bedrooms": 2,
"limit": 20
}
2. get_random_properties
Get random properties for market analysis.
Parameters:
city(optional): City namestate(optional): State abbreviationzipCode(optional): ZIP codelimit(optional): Number of properties (default: 10, max: 50)
3. analyze_market
Get comprehensive market statistics and trends.
Parameters:
zipCode(optional): ZIP code for analysiscity(optional): City namestate(optional): State abbreviationdataType(optional): "All", "Sale", or "Rental" (default: "All")
4. get_property_value
Get automated property value estimates.
Required (one of):
address: Full property addresslatitude+longitude: GPS coordinatespropertyId: Unique property identifier
Optional:
propertyType: Property typebedrooms: Number of bedroomsbathrooms: Number of bathroomssquareFootage: Property size in sq ft
Example:
{
"address": "1011 W 23rd St, Austin, TX 78705",
"propertyType": "Apartment",
"bedrooms": 1,
"bathrooms": 1
}
5. get_rent_estimates
Get long-term rent estimates with comparable properties.
Required (one of):
address: Full property addresslatitude+longitude: GPS coordinatespropertyId: Unique property identifier
Optional:
propertyType: Property typebedrooms: Number of bedroomsbathrooms: Number of bathroomssquareFootage: Property size in sq ft
6. get_sale_listings
Get current properties for sale.
Parameters:
city(optional): City namestate(optional): State abbreviationzipCode(optional): ZIP codelimit(optional): Maximum results (default: 15, max: 50)
7. get_rental_listings
Get current properties for rent.
Parameters:
city(optional): City namestate(optional): State abbreviationzipCode(optional): ZIP codelimit(optional): Maximum results (default: 15, max: 50)
8. get_property_details
Get detailed property information.
Parameters:
id(required): Property or listing ID
9. get_server_status
Get server status and API usage information.
Parameters: None
🔧 Configuration
Environment Variables
| Variable | Description | Default | Required |
|---|---|---|---|
RENTCAST_API_KEY |
Your Rentcast API key | - | ✅ |
RENTCAST_BASE_URL |
Rentcast API base URL | https://api.rentcast.io/v1 |
❌ |
MAX_API_CALLS_PER_SESSION |
Maximum API calls per session | 40 |
❌ |
TIMEOUT_SECONDS |
API call timeout | 30 |
❌ |
ENABLE_RATE_LIMITING |
Enable rate limiting | true |
❌ |
RATE_LIMIT_PER_MINUTE |
Rate limit per minute | 60 |
❌ |
DEBUG |
Enable debug mode | false |
❌ |
LOG_LEVEL |
Log level | INFO |
❌ |
API Limits
- Free Tier: 45 API calls per month
- Default Session Limit: 40 calls per session
- Rate Limiting: 60 calls per minute (configurable)
🏗️ Project Structure
mcp_rentcast/
├── src/
│ ├── index.ts # Main MCP server implementation
│ ├── services/
│ │ ├── config.ts # Configuration service
│ │ └── rentcast-api.ts # Rentcast API client
│ └── types/
│ └── index.ts # TypeScript type definitions
├── dist/ # Compiled JavaScript output
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── .env.example # Environment variables template
├── .gitignore # Git ignore patterns
└── README.md # This file
🚀 Development
Scripts
# Build the project
npm run build
# Start in development mode with hot reload
npm run dev
# Start production server
npm start
# Run tests
npm test
# Lint code
npm run lint
# Format code
npm run format
Building
# Development build
npm run build
# The compiled output will be in the `dist/` directory
Debug Mode
The server includes comprehensive console logging for debugging:
- Input Parameters: Logs all parameters received by tools
- API Responses: Logs API call results and data samples
- Error Handling: Detailed error logging with context
- Performance: API call counts and rate limiting information
🔍 Debugging
Console Logs
Each tool provides detailed logging:
🔍 [tool_name] Tool called with params: { ... }
🔍 [tool_name] Built search params: { ... }
🔍 [tool_name] API result: { ... }
🔍 [tool_name] Data sample: { ... }
🔍 [tool_name] Tool completed successfully
Common Issues
- Missing API Key: Ensure
RENTCAST_API_KEYis set in.env - API Limits: Monitor remaining API calls with
get_server_status - Rate Limiting: Wait between API calls if rate limited
- Invalid Parameters: Check parameter validation in console logs
📊 API Usage Optimization
Best Practices
- Batch Requests: Use higher limits when possible to reduce API calls
- Caching: Implement caching for frequently requested data
- Parameter Validation: Provide accurate parameters for better results
- Error Handling: Implement proper error handling for failed requests
Rate Limiting
- Default: 60 calls per minute
- Configurable via
RATE_LIMIT_PER_MINUTE - Automatic delays between calls when enabled
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
🔗 Links
🆘 Support
For issues and questions:
- Check the console logs for debugging information
- Verify your API key and configuration
- Check Rentcast API status and limits
- Open an issue in the repository
Built with ❤️ for the MCP community
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.