Guozhen AIGlobal AI field notes and model intelligence

Realtime AI News

Amap opens 20 years of location data with the Yunrui spatiotemporal intelligence agent platform

On August 18, Amap (Gaode Maps) launched its Yunrui spatiotemporal intelligence agent platform, packaging more than 20 years of location data — covering 300+ cities, 7 million merchants, and over 200 million POIs — into callable AI capabilities. Five industry agents for transportation, tourism, industry, EV charging, and commerce went live, with developers able to invoke the data via the MCP protocol.

Published
高德开放20年时空数据,发布云睿·时空智能体平台
Image source: play.google.com

On August 18, Amap (Gaode Maps) launched the Yunrui Spatiotemporal Intelligence Agent Platform, packaging its long-accumulated location data capabilities into callable AI services through a combination of a technology platform and an agent cluster.

Five industry agents — transportation, tourism, industry, EV charging, and commerce — went live at the same time, with tiered offerings for different users. Developers can call spatiotemporal data capabilities via the MCP protocol to freely compose their own agents; enterprise customers can pick services by agent type, data dimension, and call volume; and small merchants and frontline staff can directly use the industry agents for data analysis and decision support.

The underlying asset is more than 20 years of spatiotemporal data accumulated by Amap, covering over 300 cities, 7 million merchants, and more than 200 million POIs. On top of that, Amap uses a three-layer MCP, Skill, and Agent architecture to turn data into AI-callable capabilities.

MCP encapsulates capabilities such as regional traffic flow analysis, business district diagnosis, and business format distribution into standardized MCP servers that other AI applications can call directly; Skill layers industry methodology on top and is opened to developers through a standardized Skill marketplace; Agent provides out-of-the-box agents that complete analysis through conversation and output reports. Amap summarizes the relationship as "MCP is the brick, Skill is the prefab, Agent is the furnished apartment."

The platform builds on existing practice: the transportation Skill "Gaode Wendao" is being promoted among traffic management customers, while the commerce agent "Gaode Wendian" performs business district heat assessment, business format scanning, and rent-per-area efficiency analysis, generating structured reports. It entered public beta in June and now cooperates with MYbank to offer small merchants "site selection + operations + finance" services.

The newly launched charging agent "Shensuan" provides charging station site selection and operations analysis for charging network operators, while the tourism agent helps scenic area managers optimize visitor flow and layout. On the ecosystem side, Yunrui's spatiotemporal intelligence services are already accessible via MCP through platforms including Alibaba Cloud Bailian, Qianwen Office, and Lingyang Agent One.

For map companies, combining spatiotemporal data with agents is becoming a new differentiation point. By opening its 20 years of data assets as AI services, Amap gives developers a new data foundation while opening a B2B commercialization path for itself.

Why it matters

Amap's move turns 20 years of location data into MCP-callable agent services, opening a new "data + agent" B2B path for the mapping industry.

高德地图智能体MCP
Back to realtime news

Nearby Updates

All