> ## Documentation Index
> Fetch the complete documentation index at: https://helpdesk.magica.com/helpdesk/llms.txt
> Use this file to discover all available pages before exploring further.

# Should I use Super Agent, Nodes, API, or MCP?

Choose the surface based on the outcome you want and how much direct control you need.

| Your goal                                  | Best place to start |
| ------------------------------------------ | ------------------- |
| Complete a one-time or open-ended task     | **Super Agent**     |
| Run one model or utility directly          | **Nodes**           |
| Call Magica from your own software         | **API**             |
| Let an MCP-compatible AI client use Magica | **MCP**             |

## Use Super Agent for outcomes

Choose **Super Agent** when you know the result you want but do not want to design every step. It can research, browse, work with files, create content, build code, use connected apps, and coordinate multiple tools.

Example: “Research five competitors, compare their positioning, and create an executive summary.”

[Open Super Agent](https://magica.com/app/chat)

## Use Nodes for one direct model run

Choose **Nodes** when you already know the type of model or tool you need and do not need an agent or multi-step task.

Example: run an image generator, transcription model, LLM, or media utility directly.

[Open Nodes](https://magica.com/app/nodes)

## Use API or MCP for external access

Use the **API** when your application or backend should call Magica programmatically. Use **MCP** when a compatible AI client should discover and use Magica tools.

The public API and MCP surfaces focus on models and Nodes. Super Agent tasks are not exposed as a public API.

[View API and MCP documentation](https://magica.com/docs)