SonarQube MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to SonarQube code quality, security, and project analytics data.
README
SonarQube MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to SonarQube code quality, security, and project analytics data.
Features
- Project Listing: Get comprehensive project information with quality metrics
- Project Metrics: Fetch detailed quality metrics including coverage, duplication, maintainability
- Issue Management: List and analyze code quality issues with filtering capabilities
- Security Analysis: Get detailed security vulnerability and hotspot information
- Quality Gates: Check quality gate status and conditions
- Historical Analysis: View project evolution and quality trends over time
Installation
npm (Recommended)
# Global installation
npm install -g mcp-sonarqube
# Local installation in your project
npm install mcp-sonarqube
From Source
- Clone the repository:
git clone https://github.com/akhilthomas236/sonarqube-mcp-npm.git
cd sonarqube-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
Quick Start
1. Install the package
npm install -g mcp-sonarqube
2. Set up environment variables
export SONARQUBE_URL="http://your-sonarqube-instance:9000"
export SONARQUBE_TOKEN="your-sonarqube-token"
3. Run as MCP Server
mcp-sonarqube
4. VS Code Integration
Create .vscode/mcp.json in your workspace:
{
"servers": {
"sonarqube": {
"command": "npx",
"args": ["mcp-sonarqube"],
"env": {
"SONARQUBE_URL": "http://localhost:9000",
"SONARQUBE_TOKEN": "your-sonarqube-token-here"
}
}
}
}
Then use with GitHub Copilot:
@copilot List all projects in our SonarQube instance
@copilot Show me quality metrics for project "my-app"
@copilot What are the critical security vulnerabilities in project "api-service"?
Getting a SonarQube Token
- Log in to your SonarQube instance
- Go to User > My Account > Security
- Generate a new token with appropriate permissions
- Use this token as your
SONARQUBE_TOKEN
Usage
Running the Server
npm start
The server runs on stdio transport and communicates via the Model Context Protocol.
Available Tools
1. list_projects
Lists all projects in your SonarQube instance with key metrics.
Parameters:
search(optional): Filter projects by name or keyqualityGate(optional): Filter by quality gate status (OK, WARN, ERROR)organization(optional): Filter by organization (SonarCloud)
2. get_project_metrics
Get comprehensive metrics for a specific project.
Parameters:
projectKey(required): The SonarQube project keybranch(optional): Branch name (defaults to main branch)metrics(optional): Comma-separated list of specific metrics
3. list_issues
List code quality issues with filtering options.
Parameters:
projectKey(required): The SonarQube project keybranch(optional): Branch nametypes(optional): Issue types (BUG, VULNERABILITY, CODE_SMELL)severities(optional): Severities (BLOCKER, CRITICAL, MAJOR, MINOR, INFO)statuses(optional): Statuses (OPEN, CONFIRMED, REOPENED, RESOLVED, CLOSED)assignees(optional): Assignee usernamestags(optional): Issue tagslimit(optional): Maximum number of issues (default: 50)
4. get_security_vulnerabilities
Get detailed security vulnerability analysis.
Parameters:
projectKey(required): The SonarQube project keybranch(optional): Branch nameseverities(optional): Filter by severitiesstatuses(optional): Filter by statusesassigned(optional): Filter by assigned/unassignedlimit(optional): Maximum number of vulnerabilities (default: 50)
5. get_quality_gate
Check quality gate status and conditions.
Parameters:
projectKey(required): The SonarQube project keybranch(optional): Branch name
6. get_analysis_history
View historical analysis data and trends.
Parameters:
projectKey(required): The SonarQube project keybranch(optional): Branch namefrom(optional): Start date (YYYY-MM-DD)to(optional): End date (YYYY-MM-DD)limit(optional): Maximum number of analyses (default: 10)
Development
Project Structure
src/
├── index.ts # MCP server entry point
├── services/
│ └── sonarqube-client.ts # SonarQube API client
├── tools/ # MCP tool implementations
│ ├── list-projects.ts
│ ├── get-project-metrics.ts
│ ├── list-issues.ts
│ ├── get-security-vulnerabilities.ts
│ ├── get-quality-gate.ts
│ └── get-analysis-history.ts
├── types/
│ └── sonarqube.ts # TypeScript type definitions
└── utils/
└── formatting.ts # Utility functions
Scripts
npm run build- Build the TypeScript projectnpm run dev- Run in development mode with ts-nodenpm start- Start the MCP servernpm test- Run tests
Adding New Tools
- Create a new tool file in
src/tools/ - Implement the tool schema and handler function
- Add the tool to the imports and tools array in
src/index.ts - Add a case for the tool in the CallTool handler
VS Code Integration
To use this MCP server with VS Code and Copilot:
Method 1: Using npx (Recommended)
- Create
.vscode/mcp.jsonin your workspace:
{
"servers": {
"sonarqube": {
"command": "npx",
"args": ["mcp-sonarqube"],
"env": {
"SONARQUBE_URL": "http://localhost:9000",
"SONARQUBE_TOKEN": "your-token-here"
}
}
}
}
Method 2: Using local installation
If you have the package installed locally:
{
"servers": {
"sonarqube": {
"command": "node",
"args": ["./node_modules/mcp-sonarqube/dist/index.js"],
"env": {
"SONARQUBE_URL": "http://localhost:9000",
"SONARQUBE_TOKEN": "your-token-here"
}
}
}
}
Method 3: Global installation
If you have the package installed globally:
{
"servers": {
"sonarqube": {
"command": "mcp-sonarqube",
"env": {
"SONARQUBE_URL": "http://localhost:9000",
"SONARQUBE_TOKEN": "your-token-here"
}
}
}
}
- Install the MCP extension for VS Code
- The SonarQube tools will be available in Copilot Chat
Examples
Check Project Quality
@copilot Use the SonarQube tools to give me a quality overview of project "my-app"
Security Analysis
@copilot Show me all security vulnerabilities in project "my-app" that are CRITICAL or BLOCKER
Quality Gate Status
@copilot Check if project "my-app" passes its quality gate
Historical Trends
@copilot Show me the quality trends for project "my-app" over the last month
Error Handling
The server provides detailed error messages for common issues:
- Missing environment variables
- Invalid project keys
- SonarQube connection issues
- Authentication failures
- Invalid parameters
Troubleshooting
"Server exited before responding to initialize request"
If you encounter this error in VS Code or when using the MCP server, try these solutions:
-
Test the server directly first:
# Test if the server starts correctly node dist/index.js # Should output: "SonarQube MCP Server started successfully" # Test with an MCP initialize request echo '{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {"protocolVersion": "2024-11-05", "capabilities": {}, "clientInfo": {"name": "test", "version": "1.0.0"}}}' | node dist/index.js -
For VS Code integration issues:
- Make sure the package is installed globally:
npm install -g mcp-sonarqube - Try using the full path instead of
npx:{ "servers": { "sonarqube": { "command": "node", "args": ["/path/to/global/node_modules/mcp-sonarqube/dist/index.js"], "env": { "SONARQUBE_URL": "http://localhost:9000", "SONARQUBE_TOKEN": "your-token" } } } } - Restart VS Code after changing the MCP configuration
- Make sure the package is installed globally:
-
For npx issues:
- Clear npm cache:
npm cache clean --force - Reinstall the package:
npm uninstall -g mcp-sonarqube && npm install -g mcp-sonarqube - Check Node.js version (requires Node.js 18+)
- Clear npm cache:
-
Environment variable issues:
- Ensure
SONARQUBE_URLandSONARQUBE_TOKENare properly set - Test connection:
curl -u your-token: $SONARQUBE_URL/api/projects/search
- Ensure
SonarQube API Parameter Errors
If you encounter API errors related to invalid parameters:
-
"additionalFields components must be one of..."
- This error has been fixed in version 1.0.2+
- Update to the latest version:
npm update -g mcp-sonarqube - The server now uses valid
additionalFieldsvalues:rules,users,comments
-
Invalid parameter values:
- Check that your SonarQube version supports the API endpoints being used
- Some parameters may have different valid values in different SonarQube versions
- Refer to your SonarQube instance's API documentation at:
{SONARQUBE_URL}/web_api
Network and Authentication Issues
-
Connection errors:
- Verify SonarQube URL is accessible
- Check firewall settings
- Ensure SonarQube server is running
-
Authentication errors:
- Verify token is valid and has appropriate permissions
- Check token expiration
- Ensure token has at least "Browse" permission on projects
-
SSL/TLS issues:
- For self-signed certificates, you may need to set
NODE_TLS_REJECT_UNAUTHORIZED=0(not recommended for production)
- For self-signed certificates, you may need to set
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details
Links
- npm Package: https://www.npmjs.com/package/mcp-sonarqube
- GitHub Repository: https://github.com/akhilthomas236/sonarqube-mcp-npm
- SonarQube Documentation: https://docs.sonarqube.org/
- Model Context Protocol: https://modelcontextprotocol.io/
Support
For issues and questions:
- Check the SonarQube API documentation
- Verify your token permissions
- Ensure network connectivity to SonarQube
- Check the server logs for detailed error messages
- Create an issue on GitHub
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。