Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Housing Sentinel Open API(房哨兵开放API), 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%2Fhousingsentinel.cn%2Fhousingsentinel" | 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%2Fhousingsentinel.cn%2Fhousingsentinel" | 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 Housing Sentinel Open API(房哨兵开放API) API.
Read the current market phase signal for every city your plan can access, with a since cursor that returns only cities that changed
Fetch one city's signal with first-hand and second-hand inventoryCycle, inventory, and avgMonthly figures
Pull a city's daily metric series between from and to dates for trend analysis
Retrieve up to 400 raw daily transaction and inventory records for a city
GET STARTED
Read a public daily card for a city without an API key
Register, list, test, and delete webhooks for data.updated and phase.changed events
Patterns agents use Housing Sentinel Open API(房哨兵开放API) API for, with concrete tasks.
★ Agent property market briefings
An AI agent preparing a daily Chinese property market note needs each city's current phase and the reason behind it. Through Jentic it calls the signals snapshot, reads each city's phase and phaseSource, and summarises which cities sit in a defensive or buying phase, with the key held by your own instance rather than the agent.
Call GET /signals, then list each city's phase and inventoryCycle from the firstHand stats in a short briefing
Change-driven monitoring
Data updates once a day, so polling every minute wastes quota. A client stores the nextSince value from GET /signals and passes it back as since, getting only cities whose data changed, or sends If-None-Match with the last ETag to receive a 304 when nothing moved.
Call GET /signals with since set to the stored nextSince value and report only the cities returned
Phase change alerts by webhook
An investor wants to hear when Shenzhen or Hangzhou leaves a defensive phase. POST /webhooks registers an https url with a cities list and events such as phase.changed, the push carries previousPhase and the new phase, and the test endpoint sends a ping to confirm delivery.
Call POST /webhooks with url set to an https endpoint, cities set to shenzhen and hangzhou, and events set to phase.changed, then call POST /webhooks/{id}/test
Inventory cycle trend analysis
An analyst comparing cities needs a daily series, not a snapshot. GET /cities/{city}/metrics returns daily inventory cycle, inventory, and average monthly sales between from and to dates, and GET /cities/{city}/history returns raw daily transaction and inventory rows, so the analyst can chart how fast stock is clearing.
Call GET /cities/{city}/metrics with city set to guangzhou and a from and to date range covering the last quarter, then chart the inventory cycle
10 endpoints — the housing sentinel api turns official daily property transaction records for 12 major chinese cities, including shenzhen, shanghai, beijing, and guangzhou, into a market phase signal for each city.
METHOD
PATH
DESCRIPTION
/signals
Market signal snapshot for all accessible cities
/cities/{city}/signal
One city's current market signal
/cities/{city}/metrics
Daily metric series
/cities/{city}/history
Raw daily transaction and inventory records
/cities/{city}/card
Public daily card, no key
/webhooks
Register a webhook
/signals
Market signal snapshot for all accessible cities
/cities/{city}/signal
One city's current market signal
/cities/{city}/metrics
Daily metric series
/cities/{city}/history
Raw daily transaction and inventory records
/cities/{city}/card
Public daily card, no key
/webhooks
Register a webhook
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Housing Sentinel by hand means generating an hs_live_ bearer key, handling tier-dependent city access and history depth, and managing since cursors and ETags to avoid wasted polls. Through Jentic you install once, import Housing Sentinel from the API Directory, store the key once, and your agent calls it.
Permission scoping
Housing Sentinel puts the city code in the URL path (/cities/{city}/...), so a rule can pin your agent to one city such as /cities/shenzhen and the operations you pick. You choose the operations it may call, so webhook registration and deletion are not included unless you add them.
Credential isolation
Your Housing Sentinel 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 'china housing market signal' or 'alert on phase change', and Jentic returns the matching Housing Sentinel operation with its input schema so the agent passes a valid city code without reading the Chinese-language reference.
Alternatives and complements available in the Jentic catalogue.
Specific to using Housing Sentinel Open API(房哨兵开放API) API through Jentic.
What authentication does the Housing Sentinel API use?
Per its OpenAPI spec, the Housing Sentinel API uses HTTP bearer authentication with an API key in the hs_live_ format, generated from your housingsentinel.cn account under the AI Agent access page. The bearer key is the default security requirement, while GET /cities/{city}/card is declared public and needs no key. Through Jentic the key is stored by your own instance and attached at call time.
Which cities does the Housing Sentinel API cover?
The city path parameter accepts 12 codes: shenzhen, shanghai, beijing, guangzhou, hangzhou, nanjing, suzhou, wuxi, chengdu, chongqing, dongguan, and xiamen. Which of them you can query depends on your tier: per the spec, the free tier keeps Shenzhen's current signal, the trial and credits pack open all 12 cities, and paid subscriptions cover a single city or all 12.
What are the rate limits for the Housing Sentinel API?
The OpenAPI spec states limits per tier: the trial allows 10 calls a minute and 100 a day, the free tier 10 a minute and 50 a day, paid subscriptions 60 a minute and 2000 a day, and the institution tier 300 a minute and 20000 a day. The spec also notes data updates once a day and recommends polling no more than hourly.
Is there a Housing Sentinel MCP server?
You don't need an MCP server to give your agent Housing Sentinel. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the signal, metrics, and webhook operations on demand without loading another server's tool definitions into its context.
How do I get a city's market signal through Jentic?
Search Jentic for 'china housing market signal', load GET /cities/{city}/signal, and pass a city code such as shenzhen. The response carries the phase, phaseSource, firstHand and secondHand stats, and thresholds. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Housing Sentinel API?
Yes. For example, allow only GET /cities/shenzhen/signal and GET /cities/shenzhen/metrics, and the agent can read Shenzhen's phase and trend but cannot register or delete webhooks or query other cities, and every call it makes is logged.
For Agents
Read daily housing market phase signals, inventory cycles, and transaction history for 12 Chinese cities, and register webhooks for data updates and phase changes.
Use for: Get the current housing market phase for Shenzhen, Check whether any city's market signal changed since my last poll, List all cities my Housing Sentinel plan can access, Retrieve Shanghai's inventory cycle trend for the last 90 days
Not supported: Does not list individual properties, provide prices per home, or cover cities outside its 12 supported codes. Use for city-level Chinese housing transaction data and market phase signals only.
The Housing Sentinel API turns official daily property transaction records for 12 major Chinese cities, including Shenzhen, Shanghai, Beijing, and Guangzhou, into a market phase signal for each city. Each signal reports a phase such as 防守期 (defensive) or 进攻/买入期 (buy), the rule that set it, and first-hand and second-hand stats like inventoryCycle, inventory, and avgMonthly against the city's thresholds. Daily metric series and raw transaction history support trend analysis, and webhooks push data.updated and phase.changed events so a client does not have to poll.
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>