CARTO 新推出的开源 Agentic Tools 库使任何 AI Agent 能够通过标准工具调用完全控制地图，包括图层、样式、分析和空间过滤器。

CARTO's new open-source Agentic Tools library gives any AI Agent full control over a map: layers, styling, analytics, and spatial filters, through standard tool calls.

@carto/agentic-deckgl 库是一个与框架无关的软件包，面向基于 CARTO + deck.gl 构建的空间应用，赋予 AI Agent 通过标准工具调用控制地图的能力。该库提供经 Zod 验证的工具定义、内置丰富地理空间知识的系统提示（system prompt）构建器，以及面向主流 AI 框架的 SDK 转换器。所有功能均通过三个高度整合的工具实现：set-deck-state、set-marker 和 set-mask-layer。这一设计是刻意为之：与其在上下文中堆砌数十个细粒度接口，不如让 Agent 直接学习 deck.gl 的 JSON 规范本身。这使 Agent 能灵活表达几乎任意可视化形式，同时该库会在规范提交至地图前对其逐项校验。安全与治理并非 CARTO 架构中的事后补救措施，而是自始即内置于架构之中。许多正在评估 AI 驱动型应用的组织，对数据驻留地、访问控制及模型治理有着严格要求。以下是 CARTO 的应对方式。 通过安全审查的架构：@carto/agentic-deckgl 库运行于您的前端，并调用您自己的后端；CARTO Maps API 位于您的前端与数据仓库之间，仅提供瓦片服务，从不向客户端暴露原始数据。MCP（Model Context Protocol）公开的工作流均为预构建且受版本控制，而非实时生成，这意味着您的安全团队可在上线前审计生产环境中实际运行的逻辑。 CARTO 多年来持续构建地理空间基础设施：数据源接入、瓦片引擎、空间 SQL、样式系统、可视化库等。Agentic Tools 将上述全部专业能力封装为面向 AI 的开箱即用工具，任何开发者均可直接上手，无需先成为 GIS 专家。系统提示构建器即为典型示例：它不仅罗列可用工具，更注入了关于 deck.gl 图层类型、CARTO 数据源函数、配色方案、筛选语法及常见工作流模式的深度知识。Agent 进入对话时，已具备构建复杂地图可视化的能力。您只需提供业务语境，地理空间语境由该库自动处理。 @carto/agentic-deckgl 中的工具负责可视化与交互；而繁重的分析型工作流（如等时圈计算、商圈分析、人口统计信息增强、跨数百万行记录的空间连接）则由 CARTO MCP Server 承担。借助 CARTO Workflows，您可以构建复杂的地理空间分析流水线（串联缓冲区生成、空间连接、地理编码、路径规划，甚至机器学习模型），并将其作为 MCP 工具对外发布，供任何兼容的 Agent 在运行时发现并调用。该库原生支持 MCP：系统提示构建器会自动向 Agent 教授何时及如何使用可用的 MCP 工具，包括异步工作流模式。当二者协同工作时，效果显著：用户以自然语言提出复杂的地理空间问题，Agent 在服务端执行分析，结果实时渲染至地图。 欢迎查阅客户案例以了解更多信息，并通过本网络研讨会观摩这些 Agentic 工具的实际运行效果。 隆重推出 CARTO Boundaries —— 加速空间应用的可视化！ 通过与预生成的矢量瓦片集进行数据连接，实现高效处理。 借助 CARTO 加速云原生空间应用开发。 探索我们专为现代地理空间数据栈打造的 API 与开发者框架。

The @carto/agentic-deckgl library is a framework-agnostic package that builds on spatial apps using CARTO + deck.gl and gives AI Agents the ability to control a map through standard tool calls. It provides tool definitions with Zod validation, a system prompt builder packed with geospatial knowledge, and SDK converters for the major AI frameworks. All of this through just three consolidated tools: set-deck-state, set-marker, and set-mask-layer. This design is deliberate. Rather than bloating the context with dozens of granular endpoints, the library teaches the agent the deck.gl JSON specification itself. This gives the agent the flexibility to express virtually any visualization, while the library validates every spec before it hits the map. Security and governance aren't afterthoughts in the CARTO architecture: they're built into it from the start. Many organizations evaluating AI-powered applications have hard requirements around data residency, access control, and model governance. Here's how CARTO addresses them. Architecture that passes security review. The @carto/agentic-deckgl library runs on your frontend and calls your backend. CARTO's Maps API sits between your frontend and your warehouse, serving tiles without ever exposing raw data to the client. MCP-exposed workflows are pre-built and version-controlled, not generated on the fly, which means your security team can audit the logic that runs in production before it goes live. CARTO has spent years building geospatial infrastructure: data sources, tiling engines, spatial SQL, styling systems, visualization libraries. The Agentic Tools package all of that expertise into AI-ready tools that any developer can pick up, without needing to become a GIS specialist first. The system prompt builder is a good example. It doesn't just list available tools: it injects deep knowledge of deck.gl layer types, CARTO source functions, color palettes, filter syntax, and common workflow patterns. The agent arrives in the conversation already knowing how to build sophisticated map visualizations. You provide the business context; the library handles the geospatial context. The tools in @carto/agentic-deckgl handle visualization and interaction. But what about heavy analytical workflows (isochrone calculations, trade area analysis, demographic enrichment, spatial joins across millions of rows)? That's where the CARTO MCP Server comes in. With CARTO Workflows, you can build complex geospatial analysis pipelines (chaining buffers, joins, geocoding, routing, and even ML models) and expose them as MCP tools that any compatible agent can discover and call at runtime. The library has first-class MCP support: the system prompt builder automatically teaches the agent when and how to use available MCP tools, including async workflow patterns. When you combine both pieces, the result is powerful: users ask complex geospatial questions in natural language, the agent executes analysis on the server, and the results render live on the map. Check out customer stories to learn more and see these agentic tools in action in this webinar. Announcing CARTO Boundaries for faster spatial app visualizations! Join data with pre-generated vector tilesets for efficient processing. Accelerate cloud native spatial app development with CARTO. Discover our APIs and developer frameworks, built for the modern geospatial data stack.