About propdata
propdata is an MCP server and CLI for retrieving Zillow property data through the APIllow API. It serves home searches and property lookups alongside listing checks and account usage details.
Key features
- 01Search by city or ZIP code
- 02Look up properties by ID, URL, or address
- 03Batch address lookups
- 04Check active listings
- 05View API quota and plan details
Use cases
- 01Find properties in a city or ZIP code
- 02Retrieve property and sales history
- 03Check whether addresses have active listings
- 04Monitor API usage and quota
MCP support
Exposes nine tools to MCP clients for property searches, individual and batch lookups, listing checks, signup, and usage checks. Property data is passed through from APIllow.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
9Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| type | string | No | Listing type, e.g. sale. |
| query | string | Yes | City or area to search, e.g. Austin TX. |
| max_items | integer | No | Maximum results to return. |
Details
From the project READMEpropdata
Zillow property data through the APIllow API: search homes by city or ZIP code, pull a single property by its Zillow ID, its listing URL or its street address, look up several addresses in one call, check which addresses currently have an active listing, create a free account, and see how much of the monthly quota is left.
Property answers come from the upstream service and are passed through untouched, so a property record carries what APIllow returns for it — identifiers, address, status and type, bed and bath counts, living area and lot size, year built, pricing and estimates, sale and tax history, a small set of comparable homes, photos, and nearby schools.
Nine tools are provided. A tenth tool in the upstream catalogue, a plan-upgrade helper whose only output is a payment link, is deliberately not part of this package.
The nine tools:
search_properties— search by city or area, with an optional listing type and a cap on how many results come back.search_by_zip— search by one or more ZIP codes.get_property— one property by its Zillow property ID.get_property_by_url— one property from its Zillow listing URL.get_property_by_address— one property by street address.get_properties_by_addresses— several street addresses looked up in a single request.check_addresses— which of a set of addresses has an active Zillow listing, with the listing URL.signup— create a free account; the API key arrives by email after verification.check_usage— current usage, quota and plan details.
Configuration
export APILLOW_API_KEY="..." # required for every tool except signup
export APILLOW_BASE_URL="https://apillow.co/api" # optional override
Without a key, every tool except signup fails with
APILLOW_API_KEY is not set, before any argument checking.
The key is sent to the API as an X-API-Key header.
CLI
Each tool is a subcommand taking one JSON argument string:
npx @reneturcios/propdata search_properties '{"query":"Austin TX","type":"sale","max_items":10}'
npx @reneturcios/propdata search_by_zip '{"zip_codes":[90210]}'
npx @reneturcios/propdata get_property '{"zpid":12345678}'
npx @reneturcios/propdata check_usage '{}'
npx @reneturcios/propdata --version
Output is the upstream JSON, printed unchanged. Exit codes:
0 on success, 1 on a runtime error (including a
validation or upstream failure), 2 on a usage error.
MCP server
npx -y @reneturcios/propdata mcp
MCP client config:
{
"mcpServers": {
"propdata": {
"command": "npx",
"args": ["-y", "@reneturcios/propdata", "mcp"],
"env": {
"APILLOW_API_KEY": "..."
}
}
}
}
Docker
docker run -i -e APILLOW_API_KEY="..." ghcr.io/cloudcorprecords/propdata
docker run --rm -e APILLOW_API_KEY="..." ghcr.io/cloudcorprecords/propdata check_usage '{}'
Development
npm install
npm run build # tsc -> dist/
npm test # tsx --test test/*.test.ts (fake fetch, no network)
npm run dev # run the CLI from source
License
MIT — Copyright (c) 2026 Rene Turcios
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.