Kura MCP Server
Enables AI assistants to manage and monitor Eclipse Kura IoT gateways through their REST APIs, supporting device configuration, deployment, and cloud connectivity.
README
Kura MCP Server
A Model Context Protocol (MCP) server that provides seamless integration with Eclipse Kura IoT gateways through their REST APIs. This server enables AI assistants and other MCP clients to interact with Kura instances for device management, configuration, and monitoring tasks.
Features
- Comprehensive Kura API Integration: Access system properties, configurations, cloud connections, deployment packages, services, and security features
- Multi-Instance Support: Connect to multiple Kura instances simultaneously
- Robust Authentication: Secure session management with automatic re-authentication
- Flexible Configuration: JSON files, environment variables, or multiple configuration sources
- Docker Support: Containerized deployment with Docker and Docker Compose
- Type Safety: Full TypeScript implementation with Zod validation
- Retry Logic: Automatic retry mechanisms for network resilience
- Health Checking: Built-in health checks for monitoring
Installation
From Source
# Clone the repository
git clone <repository-url>
cd kura-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Start the server
npm start
Using Docker
# Build and run with Docker Compose
docker-compose up -d
# Or build and run with Docker directly
docker build -t kura-mcp-server .
docker run -p 3000:3000 -v $(pwd)/kura-mcp-config.json:/etc/kura-mcp/config.json kura-mcp-server
Development Mode
# Run in development mode with auto-reload
npm run dev
Configuration
The server supports multiple configuration methods in order of precedence:
- Environment variable
KURA_MCP_CONFIGpointing to a config file ./kura-mcp-config.jsonin the current directory~/.kura-mcp-config.jsonin the home directory/etc/kura-mcp/config.jsonsystem-wide configuration- Environment variables for individual settings
Configuration File Format
Create a kura-mcp-config.json file:
{
"port": 3000,
"logLevel": "info",
"maxRequestSize": 1048576,
"requestTimeout": 30000,
"kuraInstances": {
"local-kura": {
"name": "Local Kura Development",
"host": "localhost",
"port": 8080,
"protocol": "http",
"username": "admin",
"password": "admin",
"timeout": 30000,
"retryAttempts": 3,
"retryDelay": 1000,
"validateSSL": false
},
"production-kura": {
"name": "Production Kura Gateway",
"host": "192.168.1.100",
"port": 443,
"protocol": "https",
"username": "admin",
"password": "your-secure-password",
"timeout": 30000,
"retryAttempts": 3,
"retryDelay": 1000,
"validateSSL": true
}
}
}
Environment Variables
Configure the server using environment variables:
# Server settings
export KURA_MCP_PORT=3000
export KURA_MCP_LOG_LEVEL=info
# Kura instance configuration (replace LOCAL with your instance name)
export KURA_INSTANCE_LOCAL_HOST=localhost
export KURA_INSTANCE_LOCAL_PORT=8080
export KURA_INSTANCE_LOCAL_PROTOCOL=http
export KURA_INSTANCE_LOCAL_USERNAME=admin
export KURA_INSTANCE_LOCAL_PASSWORD=admin
export KURA_INSTANCE_LOCAL_VALIDATE_SSL=false
Configuration Options
| Option | Type | Default | Description |
|---|---|---|---|
port |
number | 3000 | MCP server port |
logLevel |
string | 'info' | Log level (debug, info, warn, error) |
maxRequestSize |
number | 1048576 | Maximum request size in bytes |
requestTimeout |
number | 30000 | Request timeout in milliseconds |
kuraInstances |
object | {} | Kura instance configurations |
Kura Instance Configuration
| Option | Type | Default | Description |
|---|---|---|---|
name |
string | - | Human-readable instance name |
host |
string | - | Kura gateway hostname or IP |
port |
number | 8080 | Kura web interface port |
protocol |
string | 'http' | Protocol (http or https) |
username |
string | - | Kura username |
password |
string | - | Kura password |
timeout |
number | 30000 | Request timeout in milliseconds |
retryAttempts |
number | 3 | Number of retry attempts |
retryDelay |
number | 1000 | Delay between retries in milliseconds |
validateSSL |
boolean | true | Whether to validate SSL certificates |
Available MCP Tools
The server provides the following tools for interacting with Kura instances:
System Information
kura_get_kura_properties- Get system propertieskura_get_framework_properties- Get OSGi framework propertieskura_test_connection- Test connection to a Kura instance
Configuration Management
kura_get_configurations- Get all component configurationskura_get_configuration- Get a specific component configurationkura_update_configuration- Update component configuration
Snapshot Management
kura_get_snapshots- Get all configuration snapshotskura_create_snapshot- Create a new configuration snapshotkura_rollback_snapshot- Rollback to a specific snapshot
Cloud Connectivity
kura_get_cloud_connections- Get all cloud connectionskura_connect_cloud- Connect a cloud connectionkura_disconnect_cloud- Disconnect a cloud connection
Package Management
kura_get_packages- Get installed deployment packageskura_install_package- Install a deployment package
Service Management
kura_get_services- Get all OSGi services
Security Management
kura_get_users- Get all userskura_get_certificates- Get certificates from keystore
Usage Examples
Using with Claude Desktop
Add this server to your Claude Desktop configuration:
{
"mcpServers": {
"kura": {
"command": "node",
"args": ["/path/to/kura-mcp-server/dist/index.js"],
"env": {
"KURA_INSTANCE_LOCAL_HOST": "localhost",
"KURA_INSTANCE_LOCAL_USERNAME": "admin",
"KURA_INSTANCE_LOCAL_PASSWORD": "admin"
}
}
}
}
Basic Operations
Once connected through an MCP client, you can:
-
Check system status:
Use kura_get_kura_properties with instance "local-kura" to get system information -
Manage configurations:
Use kura_get_configurations with instance "local-kura" to list all component configurations -
Create configuration backups:
Use kura_create_snapshot with instance "local-kura" to create a configuration snapshot -
Monitor cloud connectivity:
Use kura_get_cloud_connections with instance "local-kura" to check cloud connection status
Development
Project Structure
src/
├── types/ # TypeScript type definitions
│ ├── config.ts # Configuration types
│ └── kura.ts # Kura API types
├── services/ # Core service implementations
│ ├── ConfigService.ts # Configuration management
│ ├── KuraClient.ts # Kura REST API client
│ └── McpServer.ts # MCP server implementation
└── index.ts # Application entry point
Adding New Tools
To add a new MCP tool:
- Add the tool definition in
McpServer.tssetupHandlers()method - Implement the handler logic in the
handleToolCall()method - Add corresponding API methods to
KuraClient.tsif needed - Update type definitions in
types/kura.tsas required
Testing
# Run tests
npm test
# Run tests in watch mode
npm run test:watch
# Run linting
npm run lint
Security Considerations
- Credential Management: Store sensitive credentials securely using environment variables or secure configuration files
- SSL/TLS: Enable SSL validation in production environments
- Network Security: Ensure proper network segmentation between the MCP server and Kura instances
- Access Control: Use proper authentication and authorization for Kura instances
- Container Security: Run containers with non-root users and minimal privileges
Troubleshooting
Common Issues
- Connection Failed: Check network connectivity, credentials, and Kura instance status
- Authentication Errors: Verify username/password and ensure the Kura user has proper permissions
- SSL Certificate Errors: Set
validateSSL: falsefor development or add proper certificates - Timeout Errors: Increase timeout values in configuration
Debug Mode
Enable debug logging:
export KURA_MCP_LOG_LEVEL=debug
npm start
Health Checks
Test server health:
# Check if server is responsive
curl -f http://localhost:3000/health || echo "Server not healthy"
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'feat: add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
Commit Convention
Use conventional commits:
feat:for new featuresfix:for bug fixesdocs:for documentation changesrefactor:for code refactoringtest:for test-related changeschore:for maintenance tasks
License
This project is licensed under the Eclipse Public License 2.0 - see the LICENSE file for details.
Support
For issues, questions, or contributions:
- Check existing issues
- Create a new issue with detailed information
- Consider contributing improvements via pull requests
Related Projects
- Eclipse Kura - The IoT gateway framework
- Model Context Protocol - The protocol specification
- MCP SDK - TypeScript SDK for MCP
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。