> 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/faqs/development-tools.md).

# Development Tools

[What frameworks and libraries can I use for developing custom apps with CARTO?](https://docs.carto.com/faqs/categories/development-tools/#what-frameworks-and-libraries-can-i-use-for-developing-custom-apps-with-carto)

[Are “CARTO for deck.gl” and “CARTO for React” compatible with the new version of the platform?](https://docs.carto.com/faqs/categories/development-tools/#are-carto-for-deckgl-and-carto-for-react-compatible-with-the-new-version-of-the-platform)

[How do I connect an AI agent (Claude, ChatGPT, Gemini, Copilot) to CARTO?](https://docs.carto.com/faqs/categories/development-tools/#how-do-i-connect-an-ai-agent-claude-chatgpt-gemini-copilot-to-carto)

***

#### **What frameworks and libraries can I use for developing custom apps with CARTO?**

You can use any framework or visualization library because CARTO is based on industry-standards. If there is not a hard requirement, we recommend using deck.gl for visualization and CARTO for React for creating apps that extend the platform functionality.

***

#### **Are “CARTO for deck.gl” and “CARTO for React” compatible with the new version of the platform?**

Yes, you can use both tools with the previous and the new version of the platform.

***

#### **How do I connect an AI agent (Claude, ChatGPT, Gemini, Copilot) to CARTO?**

Use [**CARTO for Agents**](/carto-for-agents/carto-for-agents.md). The [CARTO MCP Server](/carto-for-agents/mcp-server.md) plugs CARTO into any MCP-compatible AI client over a single URL — connect it and your agent can explore your data, create and edit Builder maps, run Workflows, and more in natural language. See [Connect your platform](/carto-for-agents/connect-your-platform.md) for step-by-step setup on Claude, ChatGPT, Gemini, Microsoft Copilot, Snowflake, Databricks, and others, or the [CARTO for Agents quickstart](/getting-started/quickstart-guides/connecting-carto-to-your-agents.md) to build your first map from a prompt. Coding agents can also use [CARTO Agent Skills](/carto-for-agents/agent-skills.md) and the [CARTO CLI](/carto-for-agents/cli.md).

***

#### **Does CARTO provide an SDK for the development of Mobile applications?**

CARTO does not currently offer an SDK for the development of mobile apps as a component of our cloud native platform. In order to develop mobile applications with geospatial data, we recommend using the relevant SDK of your cloud vendor, or from products such as Google Maps, Apple Maps, Mapbox or Maplibre.

Particularly for the visualization of small datasets with spatial data (< 30MB), all SDKs will support visualization of GeoJSON files (e.g. [Google’s Maps SDK for Android](https://developers.google.com/maps/documentation/android-sdk/utility/geojson)), and CARTO’s [Maps API](/carto-for-developers/reference/carto-api.md) can be the technology to serve them.

The Mobile SDK in the previous version of the CARTO platform will not be further developed, and we don’t recommend starting new projects with it.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.carto.com/faqs/development-tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.