# MCP Tools Reference

The CARTO MCP Server exposes a catalog of tools an agent can call to explore your data, render maps, and run analytical workflows. Tools fall into three categories, each with its own page in this reference.

<table><thead><tr><th width="280">Category</th><th>What it does</th><th>Tools</th></tr></thead><tbody><tr><td><a href="/pages/3u5R5lcTK8JT7zygV3oW"><strong>Platform tools</strong></a></td><td>Help the agent find the right data. List connections, browse and search tables, inspect column distributions, and locate saved maps.</td><td><code>list_connections</code>, <code>list_resources</code>, <code>search_resources</code>, <code>describe</code>, <code>list_maps</code></td></tr><tr><td><a href="/pages/cEnllyMfFblR84A3Qb8s"><strong>Interactive tools</strong></a></td><td>Render an interactive map directly inline in the chat. Ad-hoc visualizations or saved CARTO Builder maps.</td><td><code>view_map</code>, <code>load_builder_map</code></td></tr><tr><td><a href="/pages/AyFKSPLPoTBMtNk5H9a5"><strong>Workflows tools</strong></a></td><td>Run analytical workflows your organization has published as MCP tools, in sync or async mode.</td><td>Your published workflows, plus <code>async_workflow_job_get_status_v1_0_0</code> and <code>async_workflow_job_get_results_v1_0_0</code></td></tr></tbody></table>

{% hint style="info" %}
Interactive tools render inline only in MCP clients that support [MCP Apps](https://modelcontextprotocol.io/specification/2025-06-18/server/utilities/apps): Claude.ai, ChatGPT, Claude Desktop, and others. In clients that don't, the tools return a text confirmation describing what would have been rendered.
{% endhint %}


---

# Agent Instructions: 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:

```
GET https://docs.carto.com/carto-for-agents/mcp-server/tools-reference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.