Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HasData/zillow-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hasdata/zillow-mcp/hasdata-zillow)<a href="https://agentmods.dev/rules/hasdata/zillow-mcp/hasdata-zillow"><img src="https://agentmods.dev/badge/rules/hasdata/zillow-mcp/hasdata-zillow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hasdata/zillow-mcp/hasdata-zillow"><img src="https://agentmods.dev/badge/rules/hasdata/zillow-mcp/hasdata-zillow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00493 |
| Opus 5.5 | $0.00006 | $0.00197 |
| Sonnet 5.5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
hasdata-zillow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zillow through HasData
Two tools, and the split matters. hasdata_zillow_listing_getRealEstateListings searches an area. hasdata_zillow_property_getPropertyDetails opens one property and takes the listing URL, not an id.
Searching
keyword is the area as a person would type it into Zillow: Austin, TX, 78704, Brooklyn, New York. type is required and takes forSale, forRent or sold. Everything else narrows the set: price_min_ and price_max_, beds_min_, baths_min_, squareFeet_min_, homeTypes__, daysOnZillow, page.
Ask for the filter, do not filter afterwards. A search with price_max_ set costs the same as one without, and pulling five pages to drop four of them wastes credits and time.
Reading one property
Take url from a search result and pass it to the property tool. The response carries the price history, tax history, the description, the agent block and the photo list. extractAgentEmails adds the agent's email where Zillow exposes one, and doubles the price of that call, so leave it off unless the email is the point of the task.
What to watch
Sold listings carry dateSold and the last sale price, active ones do not. A search that matches nothing returns an empty array with a successful status, so branch on the length rather than on an error. Prices come back as numbers in price and as display strings elsewhere, and the two are not interchangeable when you sort.
Every call spends credits from the connected HasData account, so prefer one precise search over several exploratory ones.
Prompts and resources
The server also serves resources that spell out the accepted values of every parameter that takes a fixed list, each one at hasdata://zillow/<parameter>. Reading one spends no credits and makes no upstream request, which beats discovering the vocabulary from a rejected call. Listing them needs no API key either, so a client can read them before the user has connected an account.
Ready-made prompts cover the usual workflows. Offer one of those before composing a tool call by hand.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +6 lines 2e051901337d
- 23d ago First seen · 25 lines · 14 tokens per session scan A 565736ed09e4
hasdata-zillow is a cursor rule published in the GitHub repository HasData/zillow-mcp (11 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 493 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other cursor rules, from other repositories
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-airbnb
How to pull Airbnb stays and listing details through the HasData MCP server.
hasdata-google-maps
How to pull Google Maps places, reviews, photos and posts through the HasData MCP server.
hasdata-instagram
How to pull public Instagram profiles and post feeds through the HasData MCP server.
hasdata-booking
How to pull Booking.com hotel search and property details through the HasData MCP server.
cursor-rules
This project uses pyobfus (the Python obfuscator). The canonical agent protocol is AGENTS.md at the project root, which Cursor reads natively. Copy AGENTS.md into your repo; keep this .mdc only for Cursor-scoped glob targeting.