> For the complete documentation index, see [llms.txt](https://docs.sonarsource.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sonarsource.com/sonarqube-cloud/administering-sonarcloud/ai-features/sonar-vortex.md).

# Sonar Vortex

What your SonarQube Cloud organization needs before your developers can install Sonar Vortex in their coding agents.

Sonar Vortex equips your developers' coding agents to write code that fits your project, and to check that code as it is produced. It has two halves:

* **Guide**, which gives an agent your project's context, rules, and constraints before it writes code.
* **Verify**, which analyzes the code the agent produces with the precision of a full CI analysis.

Developers reach both halves from their own machine, through the SonarQube CLI, a SonarQube agent plugin, or a locally running SonarQube MCP Server. This page covers what your organization needs in place first. To learn how the two halves work, see [Sonar Vortex](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex.md) in the Agent Centric Development Cycle documentation.

Vortex is part of Sonar Agent Essentials, a product that requires a separate subscription to your SonarQube Cloud Enterprise plan or annual Team plan. To trial or purchase Sonar Agent Essentials, contact [our Sales team](https://www.sonarsource.com/products/sonarqube/contact-sales/). See [Subscription plans](/sonarqube-cloud/administering-sonarcloud/managing-subscription/subscription-plans.md).

Because SonarQube Cloud is hosted, there is nothing to deploy and no instance-level setting to turn on. Once your organization has the subscription, your developers can install Vortex in their agents.

## Prerequisites <a href="#prerequisites" id="prerequisites"></a>

Check these for each project your developers use Vortex on:

* The project is analyzed in your CI pipeline on a [long-lived branch](/sonarqube-cloud/administering-sonarcloud/managing-organization/setting-config-at-org-level/setting-long-lived-branch-pattern.md). Vortex analysis reaches CI-level precision by restoring the analyzer context collected during a CI analysis, so a project that has never been analyzed has no context to restore. The context is stored per project and branch.
* The project uses [Architecture analysis](/sonarqube-cloud/architecture-analysis.md), for the best guidance of your developers' agents.

{% hint style="info" %}
If a Java project is analyzed using [Automatic analysis](/sonarqube-cloud/analyzing-source-code/automatic-analysis.md) rather than in a CI pipeline, Vortex analysis returns only basic results.
{% endhint %}

## What your developers need from you <a href="#what-developers-need" id="what-developers-need"></a>

| What                    | Value                                                                                                                                                                               |
| ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Your organization key   | The key of your SonarQube Cloud organization.                                                                                                                                       |
| The region URL          | `https://sonarcloud.io` for the EU region, or `https://sonarqube.us` for the US region.                                                                                             |
| A personal access token | Each developer generates their own. See [Managing personal access tokens](/sonarqube-cloud/managing-your-account/managing-tokens.md). Scoped organization tokens are not supported. |
| The project key         | The key of the project they work on, which Vortex uses to find the stored analyzer context.                                                                                         |

{% hint style="warning" %}
Vortex needs access to the files on the developer's machine, so it does not work through the SonarQube Cloud-hosted MCP server, which is reached over HTTP. Developers use the SonarQube CLI, a SonarQube agent plugin, or a locally running SonarQube MCP Server instead.
{% endhint %}

For the full instructions, point your developers at [Installing Vortex](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/how-to-guides.md).

## Related pages <a href="#related-pages" id="related-pages"></a>

* [Sonar Vortex (Agent Centric Development Cycle)](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex.md)
* [Installing Vortex (Agent Centric Development Cycle)](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/how-to-guides.md)
* [Subscription plans](/sonarqube-cloud/administering-sonarcloud/managing-subscription/subscription-plans.md)


---

# 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.sonarsource.com/sonarqube-cloud/administering-sonarcloud/ai-features/sonar-vortex.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.