Taiwan Real Price Registry 台灣實價登錄
Released已發布MCP Server for querying Taiwan's real estate transaction registry (實價登錄) via lvr.land.moi.gov.tw, providing property price data and market insights for AI agents.
台灣實價登錄 MCP Server,透過內政部實價登錄網站查詢不動產交易價格資料與市場洞察。
Available Tools可用工具
| Tool | Description |
|---|---|
query_real_price_tool |
Query real estate transactions by city, district, road, building, date range, and transaction type |
query_type options:
| Value | Description |
|---|---|
biz |
買賣(sales transactions) |
rent |
租賃(rental transactions) |
presale |
預售屋(pre-sale housing) |
saleremark |
預售屋建案(pre-sale project listings) |
Year defaults: If start_year / end_year are omitted, they default to
"last year through this year" computed at call time in the ROC calendar
(民國 = CE − 1911), so the tool never becomes stale.
Response shape: By default the tool returns dicts with friendly English
keys (address, total_price, unit_price, building_name, layout,
transaction_date, latitude, longitude, …). Field set differs by
query_type — see src/lvr/adapter.py for the
complete mappings. Pass raw=True to receive the government API's
original single-letter keys (a, tp, p, …) instead.
| 工具 | 說明 |
|---|---|
query_real_price_tool |
依縣市、鄉鎮市區、路名、門牌/社區、交易期間及類型查詢實價登錄資料 |
query_type 選項:
| 值 | 說明 |
|---|---|
biz |
買賣 |
rent |
租賃 |
presale |
預售屋 |
saleremark |
預售屋建案 |
年份預設: 若未指定 start_year / end_year,會在呼叫時動態計算為
「去年初到今年底」(民國年 = 西元 − 1911),不會因為時間流逝而過期。
回傳格式: 預設回傳已正規化的 dict,欄位使用易讀的英文 key
(address、total_price、unit_price、building_name、layout、
transaction_date、latitude、longitude …),各 query_type 的欄位
集合略有不同,完整對應表見 src/lvr/adapter.py。
若想拿原始政府 API 的單字母 key(a、tp、p …),傳 raw=True。
License授權
MIT License
MIT License
Usage ExamplesUsage Examples
查詢高雄市買賣行情
你: 我想知道高雄市鹽埕區今年的房屋售價
AI 呼叫:
query_real_price_tool(
city = "高雄市",
town = "鹽埕區",
query_type = "biz",
start_year = 115,
start_month = 1,
end_year = 115,
end_month = 12,
)
結果: 以下是 高雄市鹽埕區 115 年(1–3 月)買賣實價登錄統計,共 21 筆,其中 10 筆為特殊關係交易(親友、含租約等),以下以 一般正常交易 11 筆為主分析: ...
查詢台北市租金行情
你: 台北市信義區今年的租賃行情怎麼樣?
AI 呼叫:
query_real_price_tool(
city = "台北市",
town = "信義區",
query_type = "rent",
start_year = 114,
start_month = 1,
end_year = 114,
end_month = 12,
)
結果: 以下是 台北市信義區 115 年(1–2 月)整戶住宅租賃行情,有效筆數 80 筆: ...
查詢高雄市買賣行情
你: 查一下高雄市鹽埕區 113 年的房屋買賣實價登錄
AI 呼叫:
query_real_price_tool(
city = "高雄市",
town = "鹽埕區",
query_type = "biz",
start_year = 113,
start_month = 1,
end_year = 113,
end_month = 12,
)
結果: 回傳成交紀錄列表,每筆包含地址(a)、總價(tp)、單價(p)等欄位。
查詢台北市租金行情
你: 台北市信義區今年的租賃行情怎麼樣?
AI 呼叫:
query_real_price_tool(
city = "台北市",
town = "信義區",
query_type = "rent",
start_year = 114,
start_month = 1,
end_year = 114,
end_month = 12,
)
InstallInstall
From PyPI (recommended)
# Install as a uv-managed tool
uv tool install mcp-tw-lvr
# One-time: install the Chromium browser Playwright drives
uvx --from mcp-tw-lvr playwright install chromium
# Run the MCP server
uv tool run mcp-tw-lvr
Or with pipx:
pipx install mcp-tw-lvr
pipx run --spec mcp-tw-lvr playwright install chromium
mcp-tw-lvr
From source (contributors)
git clone https://github.com/asgard-ai-platform/mcp-tw-lvr.git
cd mcp-tw-lvr
uv sync
uv run playwright install chromium
uv run mcp-tw-lvr
# Interactive dev/test (MCP Inspector)
uv run mcp dev src/lvr/server.py
Claude Code / MCP client integration
After installing from PyPI, add to your MCP client config (e.g. ~/.claude.json
or a project-local .mcp.json):
{
"mcpServers": {
"mcp-tw-lvr": {
"command": "uvx",
"args": ["mcp-tw-lvr"]
}
}
}
Running from a local clone? Use the in-repo .mcp.json shape instead:
{
"mcpServers": {
"mcp-tw-lvr": {
"command": "uv",
"args": ["run", "mcp-tw-lvr"],
"cwd": "/path/to/mcp-tw-lvr"
}
}
}
從 PyPI 安裝(建議)
# 以 uv tool 方式安裝
uv tool install mcp-tw-lvr
# 一次性:安裝 Playwright 需要的 Chromium 瀏覽器
uvx --from mcp-tw-lvr playwright install chromium
# 啟動 MCP 伺服器
uv tool run mcp-tw-lvr
或使用 pipx:
pipx install mcp-tw-lvr
pipx run --spec mcp-tw-lvr playwright install chromium
mcp-tw-lvr
從原始碼執行(貢獻者)
git clone https://github.com/asgard-ai-platform/mcp-tw-lvr.git
cd mcp-tw-lvr
uv sync
uv run playwright install chromium
uv run mcp-tw-lvr
# 互動式開發/測試(MCP Inspector)
uv run mcp dev src/lvr/server.py
Claude Code/MCP 客戶端整合
從 PyPI 安裝後,於 MCP 客戶端設定(例如 ~/.claude.json 或專案根目錄的
.mcp.json)加入:
{
"mcpServers": {
"mcp-tw-lvr": {
"command": "uvx",
"args": ["mcp-tw-lvr"]
}
}
}
若要從本地 clone 執行,請改用專案內附的 .mcp.json 樣式:
{
"mcpServers": {
"mcp-tw-lvr": {
"command": "uv",
"args": ["run", "mcp-tw-lvr"],
"cwd": "/path/to/mcp-tw-lvr"
}
}
}
Data SourceData Source
All data is scraped from https://lvr.land.moi.gov.tw — Taiwan Ministry of the Interior's official real estate transaction registry. No API key required, but each query drives a real browser session against the live site.
所有資料均爬取自內政部不動產交易實價查詢服務網,無需 API 金鑰,但每次查詢皆會驅動真實瀏覽器對線上網站發出請求。
TestingTesting
# Fast unit-only run (no network)
uv run pytest -m "not e2e"
# Live E2E tests against the real portal (~30-60s each)
uv run pytest -m e2e -v
See CONTRIBUTING.md for the full dev workflow.
# 快速單元測試(不需網路)
uv run pytest -m "not e2e"
# 對實際網站的 E2E 測試(每個約 30-60 秒)
uv run pytest -m e2e -v
完整開發流程請參見 CONTRIBUTING.md。
Tags標籤
Need more powerful data capabilities? 需要更強大的data能力?
Upgrade to Asgard for enterprise-grade features, SLAs, and dedicated support.
升級至 Asgard 取得企業級功能、SLA 與專屬支援。
View Asgard Products →查看 Asgard 產品 →Related MCP Servers相關 MCP 伺服器
591 Real Estate 591 房地產資料
An MCP server to fetch and query real estate listings from 591.com.tw for AI assistants.
591 房地產資料 MCP Server,提供 AI 代理透過自然語言存取相關資料與功能。
buy123 Vendor Portal buy123 供應商平台
Model Context Protocol server for read-only buy123 vendor portal queries
mcp-buy123-vendor MCP Server,提供 AI 代理透過自然語言存取相關資料與功能。
CWA Weather 中央氣象署
MCP server for CWA (中央氣象署, Central Weather Administration) Open Data API. Provides 36 read-only tool...
中央氣象署 MCP Server,提供 AI 代理透過自然語言存取相關資料與功能。