> 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-for-vs-code/ai-capabilities/ides/devin-desktop.md).

# Devin Desktop

Install SonarQube for VS Code in Devin Desktop and configure SonarQube MCP Server manually.

## Installation

The SonarQube for VS Code extension can easily be installed in Devin Desktop during the Set up process, via the [Open VSX registry](https://open-vsx.org/extension/SonarSource/sonarlint-vscode), or by using Devin Desktop’s migration tool: Open your Devin Desktop command palette and type: `>Import VS Code`. See the [Welcome to Devin Desktop](https://docs.devin.ai/desktop/getting-started) page for details.

Because Devin Desktop references a mirror of Open VSX as a marketplace, installing a new instance of the SonarQube for VS Code extension is easy:

1. Open the **Extensions** view by pressing `Ctrl + Shift + X` (or `Cmd + Shift + X` on Mac).
2. Search for `sonarqube`.
3. Finish the installation by choosing **SonarQube for IDE** and selecting the **Install** button.

Once installed, use [connected mode](/sonarqube-for-vs-code/connect-your-ide/setup.md) to connect the extension to SonarQube Server or SonarQube Cloud. To connect Devin Desktop to SonarQube MCP Server, follow the [Set up the SonarQube MCP Server](#set-up-the-sonarqube-mcp-server) instructions.

### Migrate extensions from VS Code

In case you forget during the onboarding process, Devin Desktop provides a workflow to [import your configuration from VS Code](https://docs.devin.ai/desktop/getting-started#forgot-to-import-vs-code-configurations).

If you were using connected mode or the [#sonarqube-mcp-server](#sonarqube-mcp-server "mention"), your SonarQube token will not be migrated but you will be prompted to reauthenticate any connections you created in VS Code.

{% hint style="info" %}
Devin Desktop subscribers on their Team & Enterprise plans should add the SonarQube MCP Server to the list of allowed servers. Please see the Devin Desktop documentation about [Admin Controls](https://docs.devin.ai/desktop/cascade/mcp#admin-controls-teams-&-enterprises).
{% endhint %}

## SonarQube MCP Server

The SonarQube MCP Server is a Model Context Protocol (MCP) server that runs locally and enables a seamless connection between your AI agents and your SonarQube platform. The tools are designed to bridge the divide between productivity and quality. Please see the full details in the SonarQube [SonarQube MCP Server](https://docs.sonarsource.com/sonarqube-mcp-server/) documentation.

### Set up the SonarQube MCP Server

The SonarQube for VS Code **AI Integrations** view does not currently provide a self-hosted configuration-file action for Devin Desktop. Follow the [Devin Desktop quickstart guide](/sonarqube-mcp-server/setup/quickstart-guides/devin-desktop.md) to configure the MCP server manually instead.

For details about available MCP tools, see the [SonarQube MCP Server tools reference](/sonarqube-mcp-server/reference/tools.md).

## Related pages

* [AI CodeFix](/sonarqube-for-vs-code/ai-capabilities/ai-codefix.md)
* [AI integrations](/sonarqube-for-vs-code/ai-capabilities/integrations.md)
* Getting started with other [Supported IDEs](/sonarqube-for-vs-code/getting-started/ides.md)
* [Connected mode setup](/sonarqube-for-vs-code/connect-your-ide/setup.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-for-vs-code/ai-capabilities/ides/devin-desktop.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.