RentCast MCP Server (unofficial)

RentCast MCP Server (unofficial)

Enables querying the RentCast property API for rent and sale value estimates, market statistics, property records, and active listings through six read-only tools.

Category
访问服务器

README

RentCast MCP Server (unofficial)

An MCP server that lets Claude (or any MCP client) query the RentCast property API — rent and sale-value estimates, market stats, property records, and active listings — through six read-only tools.

Why it looks the way it does

  • Read-only. All six tools only read; nothing here can change a RentCast account.
  • A curated six, not a 1:1 API dump. These are the endpoints that make the best agent workflows, described so the model chains them correctly (e.g. list_active_listingsget_rent_estimate per address → rank by upside).
  • Clean errors. A bad key, an inactive subscription, or a rate-limit comes back as a plain sentence the agent can act on, not a stack trace.

Install (≈3 minutes)

git clone https://github.com/hasankhadra/rentcast-mcp.git
cd rentcast-mcp
npm install && npm run build

Then add this to your Claude Desktop config — ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows — and fully restart Claude Desktop:

{
  "mcpServers": {
    "rentcast": {
      "command": "node",
      "args": ["/absolute/path/to/rentcast-mcp/dist/index.js"],
      "env": {
        "RENTCAST_API_KEY": "your_rentcast_api_key"
      }
    }
  }
}

Replace the path with where you cloned the repo, and the key with your own from app.rentcast.io (the free tier is 50 requests/month — keep limit values modest). The six rentcast tools appear in the tools menu once Claude Desktop restarts.

Tools

Tool What it does
search_properties Search property records by address, city/state, zip, or lat-long + radius.
get_property_details Full attributes for one property, by RentCast id or address.
get_rent_estimate Long-term monthly rent estimate (AVM) for an address, with comparables.
get_value_estimate Sale-price (market value) estimate (AVM) for an address, with comparables.
get_market_stats Zip-level sale & rental market stats — averages, days on market, listing counts.
list_active_listings Currently active sale or rental listings for an area.

All tools are read-only. Prices are USD; rents are USD/month; areas are square feet.

Try it

Once it's wired into Claude Desktop, ask:

"What's the rent estimate for 5500 Grand Lake Dr, San Antonio, TX 78244? How does it compare to the zip code's average rent?"

Claude calls get_rent_estimate for the address and get_market_stats for 78244, then compares — e.g. an estimated ~$1,630/mo against the zip's ~$1,555/mo average.

And the one a human can't do in a single step against the RentCast dashboard:

"Find 3-bed active rental listings in Austin, TX under $2,500/mo, and estimate the fair-market rent for each so I can spot the underpriced ones."

Claude calls list_active_listings (rental, Austin TX, 3 bed), filters by price, then fans out get_rent_estimate per address and ranks by the gap between asking rent and estimated rent — chaining tools across the API in a way the dashboard doesn't.

Development

npm run build   # compile TypeScript → dist/
npm run dev     # tsc --watch
npm start       # run the built server on stdio

Layout: src/rentcastClient.ts is the single HTTP/auth/error layer; each tool lives in its own file under src/tools/; src/index.ts registers them and opens the stdio transport. For local testing outside Claude Desktop, copy .env.example to .env and run RENTCAST_API_KEY=... npm start.


Unofficial — built to show what an official RentCast MCP server could look like. Want it official — OAuth, full tool set, maintained under your name? Hasan Khadra · hk@hasankhadra.me · hasankhadra.me/mcp

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选