> For the complete documentation index, see [llms.txt](https://academy.carto.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.carto.com/agentic-gis/carto-for-agents.md). # Connecting your AI assistant to CARTO CARTO for Agents lets you drive the full CARTO platform from the AI assistant you already use — Claude, ChatGPT, Gemini, Microsoft Copilot, and more. Instead of clicking through the Workspace, you ask in plain language, and the agent explores your data, builds maps, runs Workflows, and returns results in the conversation. This tutorial gets you from zero to your first agent-built map, then points you to a use-case example for your platform of choice. {% hint style="info" %} The bridge between your AI assistant and CARTO is the **CARTO MCP Server**, which speaks the open [Model Context Protocol](https://modelcontextprotocol.io/). For the full setup reference, see [CARTO for Agents](https://docs.carto.com/carto-for-agents) in the product documentation. {% endhint %} ## What you'll learn * How to connect an AI assistant to your CARTO account. * How to build and edit a map from a natural-language prompt. * A concrete use-case example for each major agent platform. ## Before you begin * A [CARTO account](https://carto.com/signup) with a connected data warehouse. The built-in CARTO Data Warehouse works well for a first run. * An AI assistant that supports remote MCP servers. Claude is the quickest to connect. ## Step 1 — Get your MCP Server URL In the CARTO Workspace, open **Developers > Workflow API & MCP Server** and copy your **MCP Server URL**. It looks like `https://.api.carto.com/mcp/`. If your organization uses single sign-on, copy the **SSO login** URL instead. ## Step 2 — Connect your assistant Add the URL as a new MCP server in your assistant and sign in to CARTO when prompted. Claude connects with just the URL — there's nothing else to configure. Other platforms use a self-service OAuth client; the [Connect your platform](https://docs.carto.com/carto-for-agents/connect-your-platform) guides walk through each. {% hint style="success" %} Sign in over **OAuth** to unlock the full experience — creating and editing maps, running Workflows, and administering your org. A read-only API token is a quick alternative for exploring data. {% endhint %} ## Step 3 — Build your first map from a prompt Confirm the connection with a simple question: > *List my CARTO connections and the tables in each.* Then build a map. Paste this and swap in one of your own tables: > *Explore my CARTO data, then create a Builder map from `..`. Pick a sensible geometry or spatial-index column, style it clearly, add a legend, and keep it private. Show me the result and the link to open it in CARTO.* The agent inspects the table, composes the map, creates it in CARTO Builder, and hands back a link. On Claude, ChatGPT, and Claude Desktop, it also renders the map right in the chat. ## Step 4 — Keep going with a real use case Now that you're connected, try a workflow that matches how your team works. Pick your platform: * [Use-case examples by platform](/agentic-gis/carto-for-agents/use-cases-by-platform.md) — Claude, ChatGPT, Gemini, Microsoft Copilot, Databricks, Snowflake, and Oracle. ## Where to go next * [CARTO for Agents documentation](https://docs.carto.com/carto-for-agents) — the full reference: connecting each platform, the MCP tool catalog, Agent Skills, and the CLI. * [Workflows as MCP Tools](https://github.com/CartoDB/gitbook-academy/tree/master/agentic-gis/carto-for-agents/workflows-as-mcp-tools.md) — expose your own analytical Workflows as tools any agent can call. * [AI Agents](/agentic-gis/ai-agents.md) — build conversational agents directly inside your Builder maps. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://academy.carto.com/agentic-gis/carto-for-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.