> For the complete documentation index, see [llms.txt](https://docs.carto.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.carto.com/carto-for-agents/mcp-server/tools-reference.md).

# MCP Tools Reference

The CARTO MCP Server exposes a catalog of built-in tools an agent calls to explore data, work with maps and Workflows, and administer your organization. Related operations are grouped into a single tool that takes a discriminator parameter — for example, `explore_data` handles listing connections, browsing tables, searching, and describing columns through one `method` argument. This keeps the catalog compact so it fits comfortably inside every host's tool limit.

You don't call these tools by hand. Your agent picks the right tool and parameters from your natural-language request; this reference is here so you understand what the agent can do and can reason about its actions.

## Categories

<table><thead><tr><th width="220">Category</th><th>What it covers</th></tr></thead><tbody><tr><td><a href="/carto-for-agents/mcp-server/tools-reference/maps-tools.md"><strong>Maps tools</strong></a></td><td>Create, update, validate, read, and render Builder maps.</td></tr><tr><td><a href="/carto-for-agents/mcp-server/tools-reference/workflow-tools.md"><strong>Workflow tools</strong></a></td><td>Create, run, schedule, and inspect Workflows, plus any your team publishes as MCP tools.</td></tr><tr><td><a href="/carto-for-agents/mcp-server/tools-reference/data-tools.md"><strong>Data tools</strong></a></td><td>Explore connections and tables, run SQL, geocode, route, import/export, and enrich with the Data Observatory.</td></tr><tr><td><a href="/carto-for-agents/mcp-server/tools-reference/workspace-tools.md"><strong>Workspace tools</strong></a></td><td>Manage users, connections, credentials, projects, customizations, and activity data.</td></tr></tbody></table>

## How the tools are described

Each tool entry lists:

* **What it does** and when the agent uses it.
* Its **method** (or `operation` / `kind`) parameter, if it groups several operations, with the available values.
* The **key parameters** the agent supplies. Full parameter details — including optional fields and provider-specific options — live in each tool's own MCP description, which the agent reads at call time.
* Whether the tool is **read-only** or can **modify or delete** data. CARTO annotates every tool so hosts that ask for confirmation before destructive actions can do so.

{% hint style="info" %}
**What's available depends on how you authenticate.** Over [OAuth](/carto-for-agents/mcp-server/connecting-with-oauth.md), the agent reaches the full catalog below. Over an [API Access Token](/carto-for-agents/mcp-server/connecting-with-api-tokens.md), it reaches a read-and-discovery subset whose size depends on the token's Allowed APIs — browsing data, running SQL, polling (not starting) Workflow runs, and searching the Data Observatory — while the authoring and admin tools aren't offered. See [What a token unlocks](/carto-for-agents/mcp-server/connecting-with-api-tokens.md#what-a-token-unlocks) for the exact per-scope breakdown.
{% endhint %}

## Extend the catalog with your own Workflows

Any Workflow your organization builds can be published as an MCP tool, registering alongside the built-in tools. See [Workflow tools](/carto-for-agents/mcp-server/tools-reference/workflow-tools.md#your-published-workflows) and [Workflows as MCP Tools](/carto-user-manual/workflows/workflows-as-mcp-tools.md).


---

# 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://docs.carto.com/carto-for-agents/mcp-server/tools-reference.md?ask=<question>&goal=<endgoal>
```

`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.