> 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/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex-analysis.md).

# Sonar Vortex analysis

Sonar Vortex analysis checks your agent's code changes in seconds, with the same precision as a CI scan, on SonarQube Cloud and SonarQube Server.

## Overview

Sonar Vortex verifies your agent's code inside the [agentic loop](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/agentic-loop.md) of the [Agent Centric Development Cycle](/agent-centric-development-cycle/readme.md). It performs Sonar's trusted, deterministic analysis right inside your agent, reusing the context from a previous CI analysis to deliver results in record times. This lets AI agents verify code changes with minimal latency while maintaining full CI analysis precision.

Vortex analysis works with SonarQube Cloud and with SonarQube Server. What your organization needs in place differs between the two, see [Setup](#setup).

## How it works

During a CI analysis, SonarQube collects and stores your project's context: its dependencies, compiled artifacts, type information, and build configuration, tagged by project key and branch. This is why your project must be analyzed in your CI pipeline on a long-lived branch before you can use Vortex analysis.

When your agent analyzes a file, that context is restored on demand, so the analysis runs with the same inputs as a full CI scan without recomputing any of them.

## Making verification automatic

For most agents, the SonarQube plugin configures hooks, custom instructions, or both, so that Vortex analyzes the files your agent edits without you having to ask.

For details, see the installation instructions for your agent in [Installing Vortex](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/how-to-guides.md).

## Supported languages

Sonar Vortex analysis is available for the following languages:

* Java
* JavaScript
* TypeScript
* C#
* C
* C++
* Python
* Dart
* Swift
* Kotlin
* Go
* Objective-C
* PHP
* PowerShell
* Shell
* Ruby
* Apex
* SQL
* VB.NET
* CSS
* HTML
* Terraform
* Docker
* Kubernetes
* Groovy

Taint analysis (injection vulnerabilities detection) is also supported for Java, JavaScript, TypeScript, C# and VB.NET. Secrets detection is supported for all files.

> **Note:** On SonarQube Cloud, if your Java project was analyzed using [Automatic analysis](https://docs.sonarsource.com/sonarqube-cloud/analyzing-source-code/automatic-analysis/), only basic analysis results are returned.

## Setup

Installing Vortex in your agent is the same whichever product you connect to. See [Installing Vortex](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/how-to-guides.md).

What your organization needs in place first differs:

* **SonarQube Cloud**: see [Sonar Vortex](/sonarqube-cloud/administering-sonarcloud/ai-features/sonar-vortex.md) in the SonarQube Cloud documentation.
* **SonarQube Server**: see [Sonar Vortex](https://docs.sonarsource.com/sonarqube-server/instance-administration/ai-features/sonar-vortex) in the SonarQube Server documentation.

## Related pages

* [Sonar Vortex context](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex-context.md)
* [MCP Server](https://docs.sonarsource.com/sonarqube-developer-tools/sonarqube-mcp-server/)
* [Tools](https://docs.sonarsource.com/sonarqube-developer-tools/sonarqube-mcp-server/reference/tools)


---

# 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/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex-analysis.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.