housing-sentinel-aiSAFE
房哨兵 AI 接入中心:中国12城官方房产成交数据与进攻/防守市场信号 — MCP Server + REST API + Claude Skill | Housing Sentinel: official housing data & offense/defense market signals for 12 major Chinese cities, via MCP / REST / Claude Skill
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
把中国 12 城官方房产成交数据与进攻/防守市场信号,接入你的 AI Agent 和自动化工作流
Connect official daily housing-transaction data & market signals for 12 major Chinese citiesto your AI agents and workflows.
[](https://housingsentinel.cn) [](#方式-amcp-接入claude--cursor-等推荐) [](https://smithery.ai/servers/sdzhuang/housing-sentinel-ai) [](./openapi.yaml) [](./skills/housing-sentinel/SKILL.md) [](#覆盖城市与数据)
中文 | English
目录
- 这是什么
- 覆盖城市与数据
- 核心概念:进攻/防守市场信号
- 快速开始(3 步)
- 方式 A:MCP 接入(推荐)
- 方式 B:REST API
- 方式 C:Claude Skill
- API 一览
- 变化驱动:since / ETag 与 Webhook
- MCP Prompts 与 Resources
- npm stdio 包
- 接入配方 recipes/
- 示例与模板
- 使用规则与限制
- FAQ
- English Summary
这是什么
房哨兵是一个房产市场数据监控 SaaS:每日自动抓取各市住建局/房管局官方发布的住宅成交与库存数据,计算库存去化周期,输出"防守 / 观察 / 进攻 / 快速进攻"四档市场信号,帮助购房者和投资者把握交易时机。
本仓库是它的 AI 接入中心——通过 MCP、REST API 或 Claude Skill,把这些数据和信号接进 Claude、Cursor、扣子、Dify、n8n 或任何自建 Agent 工作流。新用户免费试用:登录生成密钥后,首次调用起 3 天内可查询全部 12 城;试用结束后深圳当前信号永久免费;点数包 ¥39/1000 次或订阅解锁全量。无需密钥的公开端点 GET /api/v1/cities/{city}/card 可直接拿到任一城市当日成交与市场档位。
📌 本仓库只包含公开接入文档与示例,不包含房哨兵实现代码。
覆盖城市与数据
12 城:深圳 · 上海 · 北京 · 广州 · 杭州 · 南京 · 苏州 · 无锡 · 成都 · 重庆 · 东莞 · 厦门
878e99ccd5f7OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add housing-sentinel-mcp --env HOUSING_SENTINEL_API_KEY=${HOUSING_SENTINEL_API_KEY} -- npx -y [email protected]Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass.
878e99ccd5f7full audit observations/trust-audit/mcp-server/sheldonzhuang__housing-sentinel-ai.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 878e99ccd5f7 | SAFE | B | 89 | first audit |
Questions
What is the housing-sentinel-ai MCP server?
房哨兵 AI 接入中心:中国12城官方房产成交数据与进攻/防守市场信号 — MCP Server + REST API + Claude Skill | Housing Sentinel: official housing data & offense/defense market signals for 12 major Chinese cities, via MCP / REST / Claude Skill
Is housing-sentinel-ai safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does housing-sentinel-ai need?
It reads HOUSING_SENTINEL_API_KEY, HS_API_KEY and HS_WEBHOOK_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does housing-sentinel-ai run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as housing-sentinel-mcp at 1.3.0.
How current is this page?
The grade is for one exact copy of the source (878e99ccd5f7), read on 2026-10-11. The repository is watched and re-audited when it changes.