> 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/ai-capabilities.md). # AI capabilities Explore Sonar Vortex, Hunter Agent, Remediation Agent, AI CodeFix, and tools for working with coding agents in SonarQube Cloud. Use SonarQube Cloud's AI capabilities and coding-agent integrations to give agents project context, check code changes, find vulnerabilities, and get fix suggestions. For the broader development workflow, see [Agent Centric Development Cycle](https://docs.sonarsource.com/agent-centric-development-cycle/). Subscription requirements vary by feature. See the [subscription plan comparison](/sonarqube-cloud/administering-sonarcloud/managing-subscription/subscription-plans.md#comparison-table). ## Sonar Vortex [Sonar Vortex context](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex-context.md) gives your agent project context and coding guidelines before it writes or edits code. [Sonar Vortex analysis](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/sonar-vortex-analysis.md) checks the code changes your agent produces, using analysis context from your project's CI pipeline. For prerequisites and setup guidance, see [Sonar Vortex](/sonarqube-cloud/administering-sonarcloud/ai-features/sonar-vortex.md). ## Gitar [Gitar](https://gitar.ai) is a separate Sonar product that provides AI-powered pull request review. It posts review comments directly in your pull requests to help you catch issues before merging. ## Hunter Agent The SonarQube Hunter Agent runs AI-powered analysis to find complex, logic-level security vulnerabilities and raises its findings as issues in SonarQube Cloud. To enable the agent and run analyses, see [Hunter Agent administration](/sonarqube-cloud/administering-sonarcloud/ai-features/hunter-agent.md). To review its findings, see [Hunter Agent findings](/sonarqube-cloud/managing-your-projects/issues/with-ai-features/hunter-agent-findings.md). ## Remediation Agent The SonarQube Remediation Agent proposes fixes for issues in your pull requests and your main branch's backlog. It opens new pull requests for you to review and approve. To enable it, see [Administer the Remediation Agent](/sonarqube-cloud/administering-sonarcloud/ai-features/administer-remediation-agent.md). To request fixes and track agent activity, see [Remediation Agent](/sonarqube-cloud/managing-your-projects/issues/with-ai-features.md#remediation-agent). ## AI CodeFix AI CodeFix uses a large language model (LLM) to generate a fix suggestion for an individual issue. You review and apply the suggestion. To enable it, see [Enable AI CodeFix](/sonarqube-cloud/administering-sonarcloud/ai-features/enable-ai-codefix.md). To request suggestions, see [Getting AI-generated fix suggestions](/sonarqube-cloud/managing-your-projects/issues/fixing.md#getting-ai-generated-fix-suggestions). ## SonarQube CLI and agent plugins [Agent plugins](/agent-centric-development-cycle/developer-tools/agent-plugins.md), the [SonarQube CLI](https://docs.sonarsource.com/sonarqube-cli/), and the SonarQube MCP Server connect your coding agent or terminal workflow to SonarQube capabilities. For Vortex setup instructions, see [Installing Vortex](/agent-centric-development-cycle/inside-your-agent-the-agentic-loop/how-to-guides.md). ## SonarQube MCP Server The [SonarQube MCP Server](https://docs.sonarsource.com/sonarqube-mcp-server/) connects your AI coding agent to SonarQube Cloud through the Model Context Protocol (MCP). Your agent can retrieve issue data, project quality status, and more. SonarQube Cloud includes a hosted MCP server with no local setup required. See [SonarQube Cloud-hosted](/sonarqube-mcp-server/setup/sonarqube-cloud-hosted.md) for setup instructions. For other agent configurations, see the [IDE/CLI quickstart guides](/sonarqube-mcp-server/setup/quickstart-guides.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/ai-capabilities.md?ask=&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.