Connect Real Estate Info Library to Copilot Studio
Query Real Estate Info Library directly from Copilot Studio. Arlet links the two through one MCP connection and takes care of API keys.
This server connects your AI client to the Real Estate Information Library API operated by Japan's Ministry of Land, Infrastructure, Transport and Tourism (MLIT), opened in April 2024.
Key features:
- List the municipalities of a prefecture with their 5-digit codes (XIT002), which feed the other tools. Prefectures can be given as a code or a name (13, 東京都, Tokyo).
- Fetch real estate transaction prices (from 2005 Q3) and agreed prices (from 2021) for a year or a single quarter, filtered by prefecture, municipality or station code (XIT001). Records include property type, location, price, floor area, building year and more, in Japanese or English.
- Fetch official land price appraisal records (kanteihyokasho, latest five years) by valuation year, prefecture and land-use division (XCT001). The 100+ Japanese fields are summarised into readable keys (price per square metre, address, zoning, coverage and floor area ratios, coordinates), with the appraisal-method breakdown available on request.
- Fetch official land price survey points around a latitude/longitude for any year from 1995 (XPT002), including prefectural surveys, with this year's and last year's price, the year-on-year change rate, zoning and the nearest station.
- Fetch projected population by 250 m grid square around a point (XKT013), grouped by projection year with age bands and ratios - the basis for catchment-area analysis.
- List railway stations around a point with their yearly passenger counts (XKT015). The station group code returned here is the code the transaction search needs to filter by station.
The tile-based APIs require XYZ tile coordinates; this server takes a latitude and longitude instead, converts them internally, and reports the map area actually covered so you can widen or move the query. The upstream API has no server-side paging and limits heavy consecutive requests, so each tool call makes exactly one upstream request and truncates results client-side with a next_start_position cursor. Arlet obtains and manages the API key, so there is nothing for you to apply for or configure - just switch the server on. (Under the upstream terms of use, heavy bursts of requests on a single key may be throttled.)
Attribution required by the terms of use: このサービスは、国土交通省の不動産情報ライブラリのAPI機能を使用していますが、提供情報の最新性、正確性、完全性等が保証されたものではありません (This service uses the API functions of MLIT's Real Estate Information Library, but the currency, accuracy and completeness of the information provided are not guaranteed).
How to connect Real Estate Info Library to Copilot Studio
- 1
In the Arlet dashboard, open Data tools, find Real Estate Info Library and switch it on. No API key setup is needed.
- 2
Sign in to Copilot Studio with your work account, create a new agent (or open an existing one), and in the Build tab choose Tools → + → Add → Model Context Protocol (MCP) in the right panel.
- 3
In the Add MCP server form, enter "Arlet" as the Server name, https://mcp.arlet.dev/mcp/ as the Server URL, choose OAuth 2.0 for Authentication and "Dynamic (detected)" for Configuration type, then click Add. No Client ID / Secret is needed.
- 4
On the Select a connection screen, choose Create new connection → Create, then sign in with Google on the Arlet authorization screen and click Allow. Click Add to attach the tool to the agent, then Publish to use it from Microsoft 365 Copilot.
Requires a Microsoft work account and a Copilot Studio license (or trial). MCP is available only for agents using generative orchestration and not in Copilot Studio in Teams.
