Agentic (System Monitoring & RAG) MCP server

The Agentic Enterprise system offers intelligent business services through an agent-based architecture using the Model Control Protocol (MCP). This sample system demonstrates how multiple services can work together to provide comprehensive business solutions, with components communicating via MCP to process user requests and deliver contextual responses.

System Overview

The architecture consists of three main components:

• Application agent - receives user requests and orchestrates other services
• RAG service - provides knowledge-based answers using a vector database
• Monitoring service - offers system status information

Installation

Prerequisites

You'll need to have Redis running for the vector database. Start it using Docker Compose:

cd environment
docker-compose up -d

Starting the Services

The system requires all three services to be running. Start them in the following order:

1. Start the RAG service:

cd rag
mvn spring-boot:run

2. Start the Monitor service:

cd monitor
mvn spring-boot:run

3. Start the Application Agent:

cd application-agent
mvn spring-boot:run

Configuration

Each service has its own configuration settings in their respective application.yml files.

Application Agent

• Port: 8080
• Dependencies: Connects to RAG and Monitor services via MCP clients
• Configuration file: Located at application-agent/src/main/resources/application.yml

RAG Service

• Port: 8081
• Type: MCP Server
• Storage: Redis Vector Store
• Configuration file: Located at rag/src/main/resources/application.yml

Monitor Service

• Port: 8082
• Type: MCP Server
• Configuration file: Located at monitor/src/main/resources/application.yml

Using the System

Once all services are running, you can interact with the system by sending requests to the application agent on port 8080. The application agent will:

1. Receive your request
2. Coordinate with the appropriate services (RAG and/or Monitor)
3. Process the information
4. Return a comprehensive response

The RAG service uses vector-based retrieval to provide contextually relevant information from its knowledge base, while the monitoring service offers system status updates as needed.

To see the system in action, you can watch the demo video included in the original repository.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.