About Zillapi Zillow Mcp
Zillapi Zillow Mcp provides property-data skills for AI agents, including Zestimates, listing searches, comparable properties, and price history. It is for agents handling U.S. real-estate research and also offers a hosted MCP server, though the README gives no server-specific details.
Key features
- 01Look up property data by address or URL
- 02Retrieve Zestimates and price history
- 03Search listings by location or bounding box
- 04Access photos, taxes, and school data
- 05Compare sale and rental listings
Use cases
- 01Estimate a property's value
- 02Find listings in a location
- 03Review a home's price history
- 04Research comparable homes and local details
MCP support
The README states that a hosted MCP server is available and that the same API key works with it, but does not describe its MCP tools or interface.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.zillapi.com/mcpclaude mcp add --transport http zillow-skills https://api.zillapi.com/mcp{"mcpServers":{"zillow-skills":{"type":"http","url":"https://api.zillapi.com/mcp"}}}Open in Cursor{"servers":{"zillow-skills":{"type":"http","url":"https://api.zillapi.com/mcp"}}}Open in VS Code{"mcpServers":{"zillow-skills":{"type":"http","url":"https://api.zillapi.com/mcp"}}}{"mcpServers":{"zillow-skills":{"serverUrl":"https://api.zillapi.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README
Zillow Skills: Property Data, Zestimates & Listings for AI Agents
Zillow Skills let your AI agent run comps, pull Zestimates, and scan for-sale, sold & rental listings across 160M+ U.S. homes, plus photos, taxes, schools, and full price history, just by asking. No code required.
Zillapi is an independent service for Zillow-sourced data, not affiliated with, endorsed by, or sponsored by Zillow.
Free to use: grab a key (100 credits, no card required) and you're calling Zillow data from Claude, ChatGPT, OpenClaw, Hermes Agent, or your own agent loop in under two minutes.
Pure Python standard library. No dependencies. MIT-0 licensed.
Install
# OpenClaw (via ClawHub)
npx clawhub@latest install zillow-full
# Hermes Agent
hermes skills install skills-sh/ZeroPointRepo/zillow-skills/skills/zillow-full
# Generic agent skills (Claude Code, Cursor, Cline)
npx skills add ZeroPointRepo/zillow-skills
Skills in this repo
| Skill | Purpose | Cost |
|---|---|---|
zillow-full | Complete property data toolkit: address lookup, URL lookup, Zestimate, search, history, photos, schools, agent | 1 credit per call |
zillow-zestimate | Zestimate-only valuation lookups (lighter response) | 1 credit per call |
zillow-search | Bounding-box and location-based listing search | 1 credit per listing returned |
Install the bundled zillow-full for agents that need broad coverage. Install the focused variants when you want minimum tool surface.
Authentication
Set the ZILLAPI_KEY environment variable to your Zillapi API key (format zk_...).
export ZILLAPI_KEY="zk_..."
Get a free key in 30 seconds: 100 credits, no card required. The same key works for these skills, the hosted MCP server, and direct REST calls.
Pricing
Free tier: 100 credits at signup, no credit card. One credit equals one property record returned. Failed calls do not consume credits. Full pricing: zillapi.com/pricing.
Source
- API reference: https://zillapi.com/openapi.json
- Hosted MCP server: https://api.zillapi.com/mcp
- Quickstart: https://zillapi.com/quickstart/
Issues and contributions
See CONTRIBUTING.md. Security reports: SECURITY.md.
License
MIT No Attribution. Fork, ship, sublicense with no attribution required.
Trademark
Zillapi is an independent service and is not affiliated with, endorsed by, or sponsored by Zillow Group, Inc. "Zillow" and "Zestimate" are registered trademarks of Zillow Group, Inc.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.