zillow

The Zillow MCP Server provides real-time access to Zillow real estate data via a Python-based FastMCP implementation. It exposes a set of interactive tools that let you search for properties, retrieve detailed property information, obtain Zestimate values, view market trends, and perform mortgage calculations. You can operate the server in stdio mode for local use or run it in HTTP mode for remote access, making it suitable for integration with Claude Desktop or other clients. The available tools are designed to be called with clear parameter inputs, and responses are returned in structured formats suitable for downstream processing.

You can interact with the server’s capabilities using the provided tools, including search_properties for location-based property searches, get_property_details for in-depth property information, get_zestimate for valuation estimates, get_market_trends for location-based market data, calculate_mortgage to estimate monthly payments, and check_health to verify API connectivity. The server supports both interactive (function-call style) usage and explicit Claude-compatible prompts, and it provides resources formatted as text resources via the zillow:// URL scheme for easy consumption in client apps.

Prerequisites:

• Python 3.8 or higher
• Git installed on your machine
• A Zillow Bridge API key (ZILLOW_API_KEY)

Installation steps:

1. Clone the repository and navigate to the project directory: git clone https://github.com/rohitsingh-iitd/zillow-mcp-server cd zillow-mcp-server

2. (Optional) Create a virtual environment and activate it: python -m venv venv source venv/bin/activate # On Windows use: venv\Scripts\activate.bat

3. Install dependencies listed in requirements.txt: pip install -r requirements.txt

4. Create a .env file (or set environment variables) with your Zillow API key: ZILLOW_API_KEY=your_zillow_api_key_here

5. Run the server locally in standard stdio mode: python zillow_mcp_server.py

6. (Optional) Run the server in HTTP mode for remote access: python zillow_mcp_server.py --http --port 8000

7. If you prefer Docker, build and run the image after ensuring the Dockerfile is present: docker build -t zillow-mcp-server . docker run -p 8000:8000 -e ZILLOW_API_KEY=your_key_here zillow-mcp-server or with an env file: docker run -p 8000:8000 --env-file .env zillow-mcp-server

Tips and considerations:

• Ensure your ZILLOW_API_KEY is kept secure and not committed to version control.
• In HTTP mode, remember to expose the correct port and configure any needed firewall rules.
• The server depends on Zillow Bridge API; if the bridge changes its interface, you may need code updates.
• When using Claude Desktop, you can configure the mcpServers mapping to point to your local or remote instance using the provided config examples.
• For production deployments, consider adding proper logging, monitoring, and rate limit handling to avoid API throttling.