Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Zillow Property Data, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fapillow.co%2Fapillow" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fapillow.co%2Fapillow" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Zillow Property Data API.
Retrieve Zillow property data by address, ZIP, city, Zillow Property ID, or URL
Return Zestimates, tax history, school ratings, and comparable sales for a property
Narrow a request with property-type and price-range filters
Fetch batch job results for a submitted property request, with CSV export
Report account usage against the monthly quota
GET STARTED
Patterns agents use Zillow Property Data API for, with concrete tasks.
★ AI agent answering property questions
A real-estate assistant needs factual property details when a user names an address. Through Jentic the agent searches for getting Zillow property data, loads the property lookup with the API key already injected, and returns the Zestimate, tax history, and school ratings for that address. The agent answers from live data rather than a stale cache.
Call POST /v1/properties with a street address and return the Zestimate, tax history, and school ratings
Property valuation lookup
An investor's agent compares a home's estimated value against recent comparable sales. The APIllow API returns a Zestimate alongside comparable sales and tax history for a property, giving the agent the inputs for a quick valuation read. This replaces manually opening Zillow for each candidate property.
Call POST /v1/properties for a Zillow Property ID and summarize the Zestimate against its comparable sales
Area market scan
An agent surveying a neighbourhood pulls properties in a ZIP code within a target price band. The APIllow API accepts a ZIP or city plus property-type and price-range filters and returns matching properties, up to the per-plan result limit, which an agent can export as CSV from the results endpoint. This builds a market snapshot without scraping listing pages.
Call POST /v1/properties with a ZIP code and a price-range filter, then GET /v1/results/{job_id} to collect the output
3 endpoints — the apillow api returns detailed zillow property data from a city, zip code, street address, zillow property id, or listing url.
METHOD
PATH
DESCRIPTION
/v1/properties
Get property data by address, ZIP, city, Zillow Property ID, or URL
/v1/results/{job_id}
Retrieve batch job results for a submitted request
/v1/usage
Report account usage against the monthly quota
/v1/properties
Get property data by address, ZIP, city, Zillow Property ID, or URL
/v1/results/{job_id}
Retrieve batch job results for a submitted request
/v1/usage
Report account usage against the monthly quota
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the APIllow API by hand means obtaining a key, sending it in the X-API-Key header, and shaping each property request with its address or ID inputs, type and price filters, and per-plan result limits. Through Jentic you install once, import APIllow from the API Directory, store the key once, and your agent calls it.
Permission scoping
The APIllow API is read-only: it looks up property data, returns batch results, and reports account usage. You choose the operations your agent may call, so you can allow the property-data lookup and leave the usage endpoint out, or include both, and the agent can never reach an operation you have not allowed.
Credential isolation
Your APIllow key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get Zillow property data' or 'look up a Zestimate', and Jentic returns the matching APIllow operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Zillow Property Data API through Jentic.
What authentication does the APIllow API use?
The APIllow API authenticates with an API key sent in the X-API-Key request header, per its OpenAPI spec. A free key covers a monthly allowance of properties with no card required. Through Jentic the key is stored once and injected at call time, so the agent never sees the raw key.
Can I get a property's Zestimate and comparable sales?
Yes. Call POST /v1/properties with an address, ZIP, Zillow Property ID, or URL and the response includes the Zestimate, tax history, school ratings, and comparable sales among its property fields. You can narrow which properties come back with property-type and price-range filters.
What are the rate limits for the APIllow API?
The OpenAPI spec does not define per-second rate ceilings. Instead each plan sets how many properties a single request may return and a monthly allowance, and you can read current consumption with GET /v1/usage. Check the APIllow documentation for your plan's figures before running large area scans.
Is there an APIllow MCP server?
You don't need an MCP server to give your agent the APIllow API. Jentic connects it directly from the API Directory: import the API, store your key once, and your agent calls operations such as POST /v1/properties on demand without loading another server's tool definitions into its context.
Can I limit what my agent is allowed to do with the APIllow API?
Yes. Write a rule that allows only the property-data lookup and the usage check, so the agent can read property details and monitor consumption and nothing else, and every call it makes is logged. Because the API is read-only, there are no write operations to worry about, but you still decide which reads are in scope.
How do I get Zillow property data through Jentic?
Search Jentic for 'get Zillow property data', load the POST /v1/properties operation, and run it after your key is stored. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Look up detailed Zillow property data by address, ZIP, city, Zillow ID, or URL, including Zestimates, tax history, school ratings, and comparable sales.
Use for: Get Zillow data for a street address, Retrieve the Zestimate for a property, Search properties in a ZIP code within a price range, Fetch comparable sales for a home
Not supported: Does not list properties for sale, handle mortgages, or manage leases. Use for retrieving Zillow property data such as Zestimates, tax history, and comparable sales only.
The APIllow API returns detailed Zillow property data from a city, ZIP code, street address, Zillow Property ID, or listing URL. Each property comes back with dozens of fields including Zestimates, tax history, school ratings, and comparable sales, and requests can be narrowed with property-type and price-range filters. A results endpoint retrieves batch output, with CSV export available, and a usage endpoint reports consumption against the monthly quota.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>