# Plus backbone and MCP tools for Neural Architecture Search

Neural Architecture Search now supports the Plus backbone for object detection. Plus discovers more accurate models and is best when you plan to deploy on cloud GPUs.

NAS training is also now available through the Roboflow MCP Server. Coding agents like Claude Code, Cursor, and Codex can start a NAS run, list and compare NAS and non-NAS models across a workspace, and pick a model to deploy through MCP.

[See Neural Architecture Search documentation](https://docs.roboflow.com/train/neural-architecture-search)

<figure><img src="/files/AUOvPx3A5xhlPc7TgCQ3" alt=""><figcaption></figcaption></figure>


---

# 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.roboflow.com/changelog/explore-by-month/may-2026/plus-backbone-and-mcp-tools-for-neural-architecture-search.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.