Zillow Leads Property Data

io.github.kmatata由 GitHub 账号 kmatata 发布v1.0.8更新于 Oct 24, 2026

MCP server for the zillow-leads-property-data actor: Zillow leads with agent contacts and history.

概览

AI 生成的概览

本地 MCP 服务器,调用 Zillow Leads & Property Data 的 Apify actor,返回含经纪人联系方式、价格与税费历史及风险标记的 Zillow 房源数据。

可以做什么
  • 以 catalog 模式运行 Zillow 线索 actor,快速取得某都市区已缓存的富化快照。
  • 以 custom_search 或 recent_activity 模式下单实时采集并取回房源结果。
  • 获取基础字段(地址、价格、卧室/浴室数、状态、面积),或含经纪人/经纪公司联系方式、价格与 20 年以上税费历史、法拍信号、学校、HOA 与 resoFacts 的富化数据。
  • 在多次下单之间沿用 zpids 与 MLS ID,避免为同一行数据重复付费。
适用场景
适合房地产线索获取与房源调研:需要助手拉取带经纪人联系方式及长期价格、税费历史的 Zillow 房源数据,可使用缓存快照或实时采集订单。
运行要求
以本地 stdio 进程在用户机器上运行(仅桌面端)。它调用 Apify actor,因此需要 Apify 账号与 Apify API 凭据,actor 按事件计费。需要访问 Apify 与 Zillow 的网络连接。
安装前请注意
该 actor 按事件计费:每 1,000 条基础数据 0.70 美元、每 1,000 条富化数据 1.20 美元,实时订单会消耗用户 Apify 账户余额。数据通过真实浏览器会话从 Zillow 抓取,富化数据包含经纪人姓名、电话和邮箱等个人联系信息。该仓库本身仅为文档与示例,并不运行 actor。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Zillow Leads Property Data,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

zillow-leads-property-data

Code samples, a sample dataset, and a full workflow notebook for the Zillow Leads & Property Data Apify actor.

The actor pulls Zillow listings enriched with agent/broker contact info, full price-history timelines, 20yr+ tax history, foreclosure/distress flags, schools, and the resoFacts long tail (heating/cooling/construction). Pay-per-event pricing, no subscription: $0.70 per 1,000 bare rows, $1.20 per 1,000 enriched rows.

Try it in 30 seconds, no signup beyond an Apify account

The actor's catalog mode returns a cached, already-enriched snapshot instantly, no bounding box, no wait:

json
{ "mode": "catalog", "metro": "Chicago" }

Run it from the Apify Console or via apify-client (see examples/ below).

What's in this repo

PathWhat it is
sample/sample_listings.csv20 real enriched rows (Chicago/Houston/Phoenix) — flat, spreadsheet-ready
sample/sample_listings.jsonlSame rows, one JSON object per line, with a nested price_history array per listing
examples/python_quickstart.pyCall the actor from Python via apify-client, wait for results, print a summary
examples/node_quickstart.jsSame, in Node, via apify-client
mcp-server/One-tool MCP server for Claude Desktop, Cursor and any MCP client; see mcp-server/README.md
notebook/zillow_leads_workflow.ipynbA realistic lead-gen workflow: run the actor, dedupe against a prior export, filter to rows with agent phone numbers, export a clean CSV

Field reference

Two depths, listings (bare) and enriched (the default):

  • listings: address, price, beds/baths, status, lot/living area, listing-type flags — whatever Zillow's own search API returns, no detail-page fetch involved. See sample_listings.csv for the shape (a subset of the columns shown there — the sample above is enriched-depth, listings-depth rows omit everything past the bare fields).
  • enriched (default): everything in listings, plus agent/broker contact (name, phone, email, brokerage, MLS attribution), full price-history and 20yr+ tax-history timelines, foreclosure/distress signals, assigned + nearby schools, HOA fees, and the resoFacts long tail (heating/cooling/parking/construction).

Full field list, pricing table, and every input mode (catalog / custom_search / recent_activity) are documented on the actor's own README.

Dedup across repeat orders

Every delivery writes a DEDUP_UPDATE record to the run's key-value store: the union of the zpids and MLS IDs you already had plus everything just shipped. Feed those two arrays back into your next order's dedupZpids/dedupMlsIds fields and you're never charged for the same row twice. See notebook/zillow_leads_workflow.ipynb for a worked example.

Use it from an AI agent (MCP)

This actor is callable as a tool via Apify's hosted MCP server (https://mcp.apify.com) or the local @apify/actors-mcp-server, no manual input-form filling required — catalog mode (the default) is a good agent smoke test since it returns cached rows in seconds with no polling loop needed. See the actor's own README for the full agent-facing input schema and the fire/poll/fetch pattern for a live-collection order.

Questions / issues

This repo is documentation and samples only — it doesn't run the actor itself. For a specific order that isn't behaving as expected, check that run's key-value store STATUS record first (the actor writes a plain-English reason there for any zero-row or partial result), then open an issue here or reach out via the actor's Apify Store page.

来源:README.md,提交 01fa450

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.8最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分