CorefluxMCPServer

Coreflux MQTT MCP Server is an enterprise-grade Model Context Protocol (MCP) server that provides secure, scalable access and automation capabilities to the Coreflux MQTT broker for Claude and other MCP-compatible AI assistants.

Purpose This server is used to connect AI assistants with the Coreflux MQTT broker, enabling them to perform MQTT-related operations, call the Coreflux API, generate LOT code, and carry out system health monitoring and connection management.

Key capabilities

• MQTT integration: seamless connection to the Coreflux MQTT broker, with full TLS support.
• Complete Coreflux API: access to models, actions, rules, and routes.
• AI code generation: generate LOT (Language-of-Things) code via the Coreflux Copilot API.
• Dynamic discovery: automatically discover and list available actions.
• Health monitoring: comprehensive system health checks and monitoring.
• Enterprise features: production-grade security (log redaction, input validation), asynchronous non-blocking processing (including rate limiting and queue management), structured logging (rotation, filtering, secure redaction), configuration validation, and complete unit tests (including mocks and coverage reports).
• DevOps: support for Docker and Kubernetes deployment (including health checks), GitHub Actions CI/CD (automated testing, security scanning, quality checks), pre-commit hooks, code formatting, linting, and documentation generation.

Available tools (tools provided to Claude) Core MQTT tools:

• publish_to_coreflux: publish a message to an MQTT topic, with support for QoS and retain options.
• get_broker_info: get MQTT broker connection details. AI assistance tools:
• copilot_assist: query the Coreflux Copilot AI for automation assistance and code generation. System management tools:
• comprehensive_health_check: performdetailed health checks on all system components. The documentation also lists the following tools:
• remove_action: remove an action event/function.
• run_action: run an action event/function.
• remove_all_models: remove all models.
• remove_all_actions: remove all actions.
• remove_all_routes: remove all routes.
• list_discovered_actions: list all discovered Coreflux actions.
• request_lot_code: generate LOT code using the Coreflux Copilot API based on a natural language prompt. Connection management tools:
• get_connection_status: get detailed connection status and troubleshooting guidance.
• setup_mqtt_connection: dynamically configure a new MQTT broker connection.
• mqtt_connect: connect to a specified MQTT broker using custom parameters.
• check_broker_health: test broker connectivity and attempt reconnection.
• reconnect_mqtt: force reconnection to the configured broker.

Usage Prerequisites: Python 3.11 or higher, Docker (optional, for containerized deployment), an accessible Coreflux MQTT broker, and a Coreflux Copilot API key (optional, for AI assistance).

Option 1: Docker deployment (recommended)

1. Clone and configure: git clone https://github.com/CorefluxCommunity/Coreflux-MQTT-MCP-Server.git cd Coreflux-MQTT-MCP-Server cp .env.example .env

Edit .env to fill in your configuration

1. Deploy using Docker: docker-compose up -d
2. Verify deployment: docker-compose logs -f coreflux-mcp-server

Method 2: Development installation

1. Clone and set up: git clone https://github.com/CorefluxCommunity/Coreflux-MQTT-MCP-Server.git cd Coreflux-MQTT-MCP-Server
2. Install dependencies: pip install -r requirements.txt

For development

pip install -r requirements-dev.txt 3. Configure environment: python setup_assistant.py

Interactive configuration

Or

cp .env.example .env && nano .env

Manual configuration

1. Validate and test: make validate make test
2. Start the server: python server.py

Or

make run

Connecting to Claude When using Claude Desktop, you need to locate the Claude Desktop configuration file: macOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %USERPROFILE%\AppData\Roaming\Claude\claude_desktop_config.json Then add the server configuration: { "mcpServers": { "coreflux": { "command": "python", "args": ["/path/to/your/server.py"], "env": { "MQTT_BROKER": "your-broker-host.com", "MQTT_PORT": "8883", "MQTT_USER": "your-username", "MQTT_PASSWORD": "your-password", "MQTT_USE_TLS": "true", "DO_AGENT_API_KEY": "your-copilot-api-key" } } } } After configuring, restart Claude Desktop. Security note: productionDeployment should store secrets in secure environment variables or a secrets management system, rather than in the Claude configuration file.

Configuration Assistant The interactive setup assistant helps configure MQTT broker connection settings, TLS certificate configuration, Coreflux Copilot API integration, logging and monitoring settings, as well as configuration validation and testing. It is suitable for initial configuration, updating settings, troubleshooting connection issues, setting up TLS certificates, or migrating between environments.

Coreflux Copilot Integration Get an API key from the Coreflux Copilot dashboard, then configure:

Method 1: Environment file

echo "DO_AGENT_API_KEY=your_api_key_here" >> .env

Method 2: Environment variable

export DO_AGENT_API_KEY=your_api_key_here It can be used for LOT code generation, automation assistance, best practice guidance, and troubleshooting.

Use Cases

• Scenarios where you want to operate a Coreflux MQTT broker through an MCP-compatible AI assistant such as Claude.
• Scenarios where you need to generate or debug LOT (Language-of-Things) automation code.
• Scenarios where you need health monitoring, connection management, and secure operations for enterprise MQTT environments.

Limitations and Notes

• Requires Python 3.11+ and an accessible Coreflux MQTT broker; Docker and a Copilot API key are both optional.
• If the MQTT broker is unreachable, the server can still start, and the connection can be troubleshooted and configured through the relevant tools.
• The materials do not provide further details on pricing, cost, platform, specific results, or usage steps.