> 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/connect-your-platform/claude.md).

# Claude

Claude.ai and Claude Desktop support **Client ID Metadata Document (CIMD)** registration, so CARTO can recognize them automatically. **No OAuth client needs to be created or registered.** Simply provide Claude with the CARTO MCP Server URL and sign in.

Both Claude.ai and Claude Desktop can also [render CARTO maps inline](/carto-for-agents/connect-your-platform.md#which-platforms-render-maps-inline) in the conversation, providing a richer experience when working with CARTO maps and spatial data.

{% hint style="info" %}
This zero-configuration OAuth flow is enabled by CIMD support. Other MCP clients may use different OAuth registration flows See [Connecting with OAuth](/carto-for-agents/mcp-server/connecting-with-oauth.md#the-simplest-path-clients-that-support-cimd) for how CARTO handles clients that lack it.
{% endhint %}

For the terminal coding agent, see [Claude Code](/carto-for-agents/connect-your-platform/claude-code.md).

## Claude.ai (web)

1. In [Claude.ai](https://claude.ai), open **Settings → Connectors**.
2. Click **Add custom connector**.
3. Enter a name, such as `CARTO`, and paste your **MCP Server URL**.
4. Click **Add**, then **Connect**.
5. You’ll be redirected to CARTO. **Sign in to authorize access.**

For more information, see Anthropic's official [Custom connectors using remote MCP documentation](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp)

<figure><img src="https://3029946802-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FybPdpmLltPkzGFvz7m8A%2Fuploads%2FElw2W0njsGCYssD8m7il%2Fimage.png?alt=media&amp;token=816b21a7-b9be-42ac-a0f0-da5911429bc3" alt=""><figcaption></figcaption></figure>

## Claude Desktop

1. Open [Claude Desktop](https://claude.com/download?utm_source=chatgpt.com) and go to **Settings → Connectors**.
2. Click **Add custom connector**.
3. Enter a name, such as `CARTO`, and paste your **MCP Server URL**.
4. Click **Add**, then **Connect**.
5. Complete the **CARTO sign-in** when prompted.

For more information, see Anthropic's [documentation on using connectors with Claude](https://support.claude.com/en/articles/11176164-use-connectors-to-extend-claude-s-capabilities)

<figure><img src="https://3029946802-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FybPdpmLltPkzGFvz7m8A%2Fuploads%2FPISNmHtQCFWiZDoz5mdk%2Fimage.png?alt=media&amp;token=f10ec35d-079d-450e-8e48-579cf28613fc" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
Claude connects over OAuth, so the agent gets the **full tool surface** — creating and editing maps, authoring Workflows, and admin. If your org uses SSO, use the **SSO login** URL from the Workspace instead.
{% endhint %}


---

# 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/connect-your-platform/claude.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.