AI capabilities

SonarQube Cloud offers a series of AI capabilities to help you produce secure and maintainable code.

SonarQube Cloud comes with a set of AI capabilities that fit in the Agent Centric Development Cycle (AC/DC), a framework that defines a continuous 3-stage loop for every AI-assisted change:

Guide → Verify → Solve

• Guide provides project context to agents before they write or edit code.
• Verify analyzes the resulting code.
• Solve fixes issues found during verification.

To learn more about AC/DC and how SonarQube Cloud features fit in the cycle, see Agent Centric Development Cycle.

AI CodeFix

SonarQube's AI CodeFix uses a large language model (LLM) to suggest fixes for issues found during analysis, the Solve stage of the AC/DC cycle. An Organization Admin enables the feature for the organization's projects.

To turn it on, see the Enable AI CodeFix page. To learn how to get fix suggestions for your issues, see the Getting AI-generated fix suggestions article.

SonarQube MCP Server

The SonarQube MCP Server is a Model Context Protocol (MCP) server that connects your AI coding agent to SonarQube Cloud. Once connected, your agent can retrieve issue data, project quality status, and more.

SonarQube Cloud includes a hosted MCP server with no local setup required. See the SonarQube Cloud-hosted page for setup instructions.

For step-by-step agent setup, see the IDE/CLI quickstart guides for the MCP server.

Related products

Gitar is a separate Sonar product that provides AI-powered pull request review automation. Gitar posts review comments directly in your pull requests to help you catch issues earlier in the development cycle.