By SonarSource
Enforce SonarQube code quality and security gates within the agent coding loop: analyze files for 7,000+ rules, detect secrets, review test coverage and duplication, fix issues with guided remediation, check quality gate status, and audit dependency risks across 40+ languages.
Analyze a file or code snippet for quality and security issues using SonarQube
Find files with low test coverage and inspect uncovered lines in a SonarQube project (project key optional when MCP integration already defines the default project)
Search for software composition analysis (SCA) dependency risks in a SonarQube project (project key optional when MCP integration already defines the default project)
Find files with code duplications in a SonarQube project and inspect duplication blocks for a file (project key optional when MCP integration already defines the default project)
Fix a specific SonarQube issue in code by rule key and location
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Made by Sonar
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages.
SonarQube combines deterministic checks with AI-assisted workflows so quality rules apply consistently to code from both developers and agents. Where your stack supports it, analysis and secrets scanning can run inside the agent loop instead of only in CI.
The Plugin helps agents connect to SonarQube CLI and SonarQube MCP Server for issue detection, checking project metrics such as test coverage and duplications, fetch dependency risks, etc. Claude Code, Copilot CLI, Codex, and Antigravity (through SonarQube CLI) install agent hooks for secrets scanning and, when entitled, Agentic Analysis.
How to use: Run /sonarqube:sonar-integrate after installation to walk through setup — CLI installation, authentication, and wiring up the MCP Server and hooks. From there, use slash commands like /sonarqube:sonar-quality-gate to check quality gates or interact naturally with prompts like "analyze my code for issues," "show open SonarQube findings," or "check my coverage." With Agentic Analysis enabled, verification happens automatically after each edit with no manual invocation required.
sonar) on your machine.Authenticate once with sonar auth login (browser flow; credentials stay in your OS keychain). The MCP server uses that login.
Check auth anytime:
sonar auth status
SonarQube CLI can wire everything for you:
sonar integrate claude # Claude Code: MCP, hooks, secrets scanning, etc.
sonar integrate copilot # GitHub Copilot CLI: MCP, hooks, secrets scanning, etc.
sonar integrate codex # Codex: MCP, hooks, secrets scanning, Agentic Analysis hook
sonar integrate antigravity # Antigravity: hooks, instructions, CAG, MCP patch (after plugin install)
Run these after sonar auth login. Use the /sonarqube:sonar-integrate skill if you prefer a guided flow (install/update CLI, login, then integrate).
Each layout includes MCP configuration (for example mcp.json or kiro-power/mcp.json) that runs the mcp/sonarqube image and relies on SonarQube CLI for authentication—the same sonar auth login session.
Antigravity uses two independent install surfaces. For full parity with Claude/Copilot you need both:
| Step | Command | What it installs |
|---|---|---|
| 1. Plugin bundle | agy plugin install <git-url|path> | Skills, agent rules (rules/sonarqube.md), MCP (mcp_config.json) |
| 2. CLI integrate | sonar integrate antigravity | Secrets hooks, Agentic Analysis instructions, Context Augmentation, MCP patch |
There is no @vendor marketplace install (for example sonarqube@sonar is not supported). Use a Git URL, archive, or local path.
| Agent | Location |
|---|---|
| Claude Code | .claude-plugin/, skills/, claude-hooks/, scripts/ |
| Cursor | .cursor-plugin/ (+ shared mcp.json) |
| GitHub Copilot CLI | .github/plugin/ (+ shared mcp.json) |
| Codex | .codex-plugin/ |
| Antigravity | plugin.json, mcp_config.json, rules/, shared skills/ |
| Gemini CLI (legacy) | gemini-extension.json, GEMINI.md |
| Kiro | kiro-power/ |
Skills are the same across agents. Ask in natural language, invoke skills explicitly, or use the SonarQube MCP tools your client shows after MCP starts.
MCP reference: SonarQube MCP Server docs.
/sonarqube:sonar-integrate
npx claudepluginhub sonarsource/sonarqube-agent-plugins --plugin sonarqubeComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review