Zillow MCP Server
A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf and any other MCP client two read-only Zillow tools. Search for-sale, for-rent and sold listings with rich filters, and read a single property in full, all as structured JSON, with nothing to host.
It reads public listing pages on Zillow.com that a signed-out visitor can see.
1,000 free credits every month, no card required, which is 100 Zillow calls at the base rate.
https://mcp.hasdata.com/mcp?apis=zillow
Contents
- What you need
- Quick start
- Example prompts
- Tools
- Errors and failure paths
- Pricing, free tier and limits
- Tool selection
- How it compares
- FAQ
- HasData links
- Development
- Contributing
- License
What you need
An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers about 100 calls a month at the 10-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/zillow-mcp on npm and hasdata-zillow-mcp on PyPI, shown below.
Quick start
The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.
Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.
claude mcp add --transport http zillow "https://mcp.hasdata.com/mcp?apis=zillow" \
--header "x-api-key: HASDATA_API_KEY"
Settings, then Connectors, then Add custom connector, then paste https://mcp.hasdata.com/mcp?apis=zillow and sign in.
For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The @hasdata/zillow-mcp package is that launcher, and it reads the key from the environment. Add this to claude_desktop_config.json:
{
"mcpServers": {
"zillow": {
"command": "npx",
"args": ["-y", "@hasdata/zillow-mcp"],
"env": { "HASDATA_API_KEY": "YOUR_KEY" }
}
}
}
For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:
{
"mcpServers": {
"zillow": {
"command": "uvx",
"args": ["hasdata-zillow-mcp"],
"env": { "HASDATA_API_KEY": "YOUR_KEY" }
}
}
}
~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:
{
"mcpServers": {
"zillow": {
"url": "https://mcp.hasdata.com/mcp?apis=zillow",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}
~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:
{
"mcpServers": {
"zillow": {
"serverUrl": "https://mcp.hasdata.com/mcp?apis=zillow",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}
.vscode/mcp.json in the workspace:
{
"servers": {
"zillow": {
"type": "http",
"url": "https://mcp.hasdata.com/mcp?apis=zillow",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}
Example prompts
Prompts, not code. Paste one in and the agent picks the tool itself. Each is annotated with the calls it takes, because every successful call costs 10 credits.
Search for-sale homes in Austin, TX with at least three beds under $600k, sorted newest first, and give me the ten most recent with price and days on market.
One call, 10 credits. Price, beds, area and days on market come back on the search result.
Take the top result and pull its full detail: price history, tax history, the price estimate, and the assigned schools.
One call, 10 credits. Those live on the property page, which the details tool reads by URL.
Find for-rent condos in Austin that allow cats, then pull the rental estimate on the three cheapest.
Four calls, 40 credits. One search, then one property call for each of the three.
For this property URL, give me the list price, the price estimate, and the last three sales in its price history.
One call, 10 credits.
A search result is enough to rank and shortlist. Price history, tax history, the estimate, schools and the agent come from the property call, so a prompt that shortlists then inspects three homes is one search plus three property calls.
Tools
Two tools, read-only. Samples below are trimmed from real calls, and the numbers move as the market moves. Read them as shapes. Each tool name links to its endpoint reference, which carries the full field list.
The samples are the payload, not the whole response. A tools/call result carries one text block, and that text is itself JSON holding url, status, text and json, with the scraped data under json. From a raw JSON-RPC response the path is result.content[0].text, parsed, then .json. A chat client unwraps that for you and code talking to the endpoint directly does not.
Get Zillow real estate listings
hasdata_zillow_listing_getRealEstateListings
A page of listings by location keyword, filtered.
The reference also documents square-footage, lot-size, year-built and HOA bands, plus otherAmenities__, views__, pets__, listingType, propertyStatus__, listingPublishOptions__ and more.
Returns searchInformation with totalResults, a properties array, and pagination whose nextPage is the URL of the following page. Each property carries id, url, homeType, status, price, currency, a rentZestimate rental estimate, daysOnZillow, area in square feet, addressRaw and a structured address, latitude, longitude, beds, baths, listingDetails, mediaDetails and photos.
{
"id": "60134551",
"url": "https://www.zillow.com/homedetails/6116-Speyside-Dr-Austin-TX-78754/60134551_zpid/",
"homeType": "SINGLE_FAMILY",
"status": "FOR_SALE",
"price": 320000,
"currency": "$",
"rentZestimate": 2286,
"daysOnZillow": 0,
"area": 2277,
"address": { "street": "6116 Speyside Dr", "city": "Austin", "state": "TX", "zipcode": "78754" },
"beds": 4,
"baths": 3
}
Get Zillow property details
hasdata_zillow_property_getPropertyDetails
One property in full, by its URL.
Returns the full page: price, currency, fees, beds, baths, area, yearBuilt, homeType, mlsId, a structured address and geo, the description and highlights, photos, schools, daysOnZillow, views, saves, an agentInfo block, and priceHistory, taxHistory and mortgage arrays. Zillow's own price estimate arrives in a zestimate object holding zestimate, an estimatedSaleRange and a rentZestimate. Read it as an estimate, not as a confirmed value.
areais an object here,{ livingArea, livingAreaUnits }, not the flat number the search tool returns. Readarea.livingAreafor the square footage on a property page, or a numeric comparison likearea > 2000silently fails against an object.
{
"id": 60134551,
"status": "FOR_SALE",
"price": 320000,
"currency": "USD",
"yearBuilt": 2002,
"beds": 4,
"baths": 3,
"area": { "livingArea": 2277, "livingAreaUnits": "Square Feet" },
"fees": { "monthlyHoaFee": "$500 annually" },
"zestimate": { "zestimate": 318100, "estimatedSaleRange": "$302K - $334K", "rentZestimate": 2286 },
"address": { "street": "6116 Speyside Dr", "county": "Travis County" },
"agentInfo": { "agentName": "Marie Coleman", "brokerName": "eXp Realty" },
"priceHistory": [{ "date": "2026-08-24", "price": 320000, "event": "listedForSale" }],
"schools": { "elementarySchool": { "name": "Bluebonnet Trail", "district": "Manor ISD" } }
}
Prompts and resources
The server ships 2 prompts, ready-made workflows a client can offer instead of making the user compose a tool call.
Alongside them the server exposes 11 resources, one per parameter whose accepted values are a fixed list. Reading one is cheaper than learning the vocabulary from a rejected call, and it costs no credits. Each URI is hasdata://zillow/<parameter>.
Both lists are served without an API key, so a client can read them before a user has signed up.
Errors and failure paths
Your client almost never sees an HTTP error code from a tool call. The MCP layer answers 200 and puts the failure inside the result, with isError set to true and the reason as text. The agent reads a message where you might expect a status line.
A wrong key surfaces as tool output, not as a failed connection. tools/list accepts any non-empty key and returns both tools, so the client completes its handshake and shows green. The first tool call then comes back with isError: true and the text HasData API error: 401 Unauthorized. Watch for that string, because nothing earlier in the flow reports the problem.
A missing key is the one real HTTP error. Authorization runs before any tool, and the connection itself fails with 401. CORS headers are present, and a browser client reads the status and not an opaque network failure.
An argument that breaks a tool's schema is rejected before it becomes a scrape. The server answers with isError: true and the text MCP error -32602: Input validation error, naming the offending field. Nothing is fetched and nothing is charged.
A search with no matches returns a successful result with an empty properties array, not an error. A location and filter set with no inventory still comes back with requestMetadata.status set to ok. Test for the array length before you iterate.
A property that has been delisted returns 400 with requestMetadata.status set to error. A URL from an old search can point at a listing that is gone.
Results that carry data also carry a requestMetadata.id worth quoting in support.
Pricing, free tier and limits
Each Zillow tool costs 10 credits per successful call. Turning on extractAgentEmails adds 5 credits to the property call, 15 instead of 10, so leave it off unless you need the email. Response size does not change the price.
The free tier is 1,000 credits every month with no card, which is 100 Zillow calls at the base rate. It renews with the billing cycle, so a low-volume agent runs on the free tier indefinitely.
Paid plans start at $59 a month for 200,000 credits, which is 20,000 calls. The unit price falls with volume, from $1.48 per 1,000 calls on the entry plan to $0.60 on Basic and $0.41 across the Growth tiers. Current figures live on the pricing page.
Your plan also sets concurrency. The free tier allows 1 request at a time, Startup 5, Basic 15, and the Growth tiers run from 50 to 500. Handle the overflow case defensively in anything unattended.
A request that comes back non-200 is not billed. A successful call that finds nothing is still a call.
Tool selection
The apis query parameter decides which tools your agent sees. Fewer tools means less context spent on tool definitions, and fewer chances for the model to reach for the wrong one.
?apis=zillow the two tools in this repo
?apis=zillow,redfin add Redfin real estate
?apis=zillow,google_maps add Google Maps places
The parameter takes provider names like zillow and individual API names like zillow_listing. Misspelled names are ignored. If every name is wrong the request fails with 400, and the body lists both what it did not recognise and every valid value. Drop the parameter and the same endpoint exposes all 57 HasData tools.
How it compares
Zillow's own API programs are for members and partners moving their own inventory, such as the Bridge Interactive and Mortgage APIs, not a self-serve way to read the public market. For searching listings and reading arbitrary properties, scraping the public pages is the route, and this server does that behind a stable schema.
What this server does not do. No posting, no lead submission, no account data. It reads what a signed-out visitor can see on Zillow.com.
FAQ
Is there an official Zillow MCP server?
Zillow does not publish one. This one is maintained by HasData and reads public Zillow.com pages.
What is a Zillow MCP server?
A server that exposes Zillow listing data as tools an AI client can call. The client sends a tool call over the Model Context Protocol, the server fetches the data and returns structured JSON, and the model works with the result. This one exposes two tools and runs remotely.
Do I need a Zillow account or API key?
No. The only credential is your HasData key. The tools read public Zillow.com pages.
Why does a search result not show price history or schools?
Because Zillow does not put them on the search card. They live on the property page, which the details tool reads by URL. Search to shortlist, then call the property tool for depth.
What does the price estimate mean?
The zestimate object holds Zillow's own estimated value, a range around it, and a rental estimate. It is a model output, not an appraisal or a confirmed sale price. Treat it as an estimate.
Can I use this together with other HasData APIs?
Yes. The apis parameter takes a list, and ?apis=zillow,redfin gives your agent Zillow plus Redfin. Drop the parameter and you get everything.
Is HasData affiliated with Zillow?
No. HasData is an independent service and is not affiliated with, endorsed by, or sponsored by Zillow Group, Inc. Zillow is a trademark of its respective owner.
Compliance and personal data
HasData accesses publicly available data only. A platform's terms may restrict automated access, and you are responsible for your own compliance. Where the data you collect includes personal information, such as a listing agent's contact details, make sure you have a lawful basis for it under GDPR, CCPA or the equivalent rules in your jurisdiction.
HasData links
Development
This repository is configuration and documentation for a remote server. There is no build step and nothing to containerize.
The tests in test/ assert the tool contract, the part that can break without a commit here. They check that ?apis=zillow returns exactly two tools, that every tool still declares its required parameters, that no name changed, and that the key in use is actually accepted. That last check calls a tool for real and costs 10 credits, which is the price of a canary that can fail for the right reason.
# macOS and Linux
HASDATA_API_KEY=your_key_here npm test
# Windows PowerShell
$env:HASDATA_API_KEY="your_key_here"; npm test
The same suite runs in CI on every push and once a week on a schedule, because the upstream tool list can change without anyone touching this repository. A failure means the tool list moved, the key stopped working, or the endpoint was unreachable, and the assertion message says which.
Contributing
Corrections to the tool tables and the response samples are the most useful contribution, because those are the parts that drift. Include the call you made and the response you got. Pull requests from forks run the suite without a key, and the live checks skip instead of going red.
License
MIT. See LICENSE.