MCP Server: ntopng MCP Server

Overview: What is ntopng MCP Server?

The ntopng MCP Server is an implementation of the Model Context Protocol (MCP) designed to enable AI applications such as Claude Desktop, Continue, and Cursor to interact with network monitoring data stored in an ntopng instance. This server acts as a bridge between AI applications and the rich datasets available from ntopng, transforming raw monitoring information into actionable insights for AI-driven tools.

🔧 Core Features & MCP Capabilities

The core capabilities of the ntopng MCP Server include:

Network Data Access

• Fetch Interface IDs: The fetch_ntopng_all_ifids command retrieves all available interface IDs from an ntopng server, providing a comprehensive view of network interfaces.

Host Information Retrieval

• Geographic Location: The get_ntopng_hosts_location tool fetches location and additional information for hosts using their IP addresses or MAC addresses.

Top Talkers Analysis

• Local & Remote Talkers: Commands like fetch_ntopng_top_local_talkers and fetch_ntopng_top_remote_talkers provide insights into the top local talkers on a specified interface, helping to identify critical communications.

Alert Statistics Collection

• Comprehensive Alerts: Tools such as get_ntopng_host_alert_stats, get_ntopng_flow_alert_stats, and get_ntopng_interface_alert_stats gather detailed statistics about various types of alerts, ensuring that the AI application has a complete understanding of network events.

Flow Data Retrieval

• Detailed Flows: Commands like query_ntopng_flows_data and get_ntopng_top-k_flows retrieve detailed data on network flows, allowing for in-depth analysis.

⚙️ MCP Architecture & Protocol Implementation

The ntopng MCP Server follows the Model Context Protocol (MCP) architecture to ensure seamless integration with various AI applications. The core components include:

Protocol Flow

The protocol flow for interactions is as follows:

1. AI Application: The MCP Client initiates a connection and sends requests via the MCP protocol.
2. nTopng MCP Server: Processes the request, interacts with the ntopng database, and generates responses based on the requested data.
3. Data Source/Tool: Provides the actual network monitoring data required by the AI application.

The following Mermaid diagram illustrates this flow:

graph TD
    A[AI Application] -->|MCP Client| B[MCP Protocol]
    B --> C[MCP Server]
    C --> D[ntopng Database]
    style A fill:#e1f5fe
    style C fill:#f3e5f5
    style D fill:#e8f5e8

nTopng Integration

The server supports integration with the ntopng database, which uses ClickHouse for historical flow and alert data storage. This ensures that the AI application can leverage powerful analytics capabilities.

🚀 Getting Started with Installation

To set up and run the ntopng MCP Server on your local machine, follow these steps:

Step 1: Prepare the Environment

Ensure that you have all required software installed, including Python, pip, and the uv framework. You can check if uv is available by running:

which uv

If not, install it using:

npm install -g @modelcontextprotocol/uv

Step 2: Set Environmental Variables

Edit the claude_desktop_config.json file to configure the connection parameters for ntopng:

{
  "mcpServers": {
    "ntopng_mcp_server": {
      "command": "/path/to/your/uv-binary",
      "args": ["run", "--with", "ntopng_mcp_server", "--python", "3.13", "."],
      "env": {
        "NTOPNG_HOST": "<ntopng-host>",
        "NTOPNG_DBPORT": "<ntopng-dbport>",
        "NTOPNG_DBUSER": "<ntopng-dbuser>",
        "NTOPNG_DBPASSWORD": "<ntopng-dbpassword>",
        "NTOPNG_API_KEY": "NTOPNG_TOKEN",
        "NTOPNG_SECURE": "true",
        "NTOPNG_VERIFY": "true",
        "NTOPNG_CONNECT_TIMEOUT": "30",
        "NTOPNG_SEND_RECEIVE_TIMEOUT": "300"
      }
    }
  }
}

Replace placeholders with actual values from your ntopng setup.

Step 3: Configure Development Environment

If you are developing the server, set up the environment variables and run the MCP Inspector:

cd mcp_ntopng
source .env
CLIENT_PORT=8077 SERVER_PORT=8078  uv dev mcp_server.py --with clickhouse-driver --with python-dotenv --with uvicorn --with pip-system-certs

💡 Key Use Cases in AI Workflows

Network Anomalies Detection

Using the ntopng MCP Server, an AI application like Continue can monitor real-time network anomalies and proactively notify security teams about potential threats. For example:

• Real-Time Alerts: The server can send alerts to Continues when unusual traffic patterns are detected on specific interfaces.

Traffic Analysis & Reporting

AI applications such as Cursor can generate detailed reports based on network flow data, providing insights into user behavior and application performance.

For instance, an engineer could use the fetch_ntopng_top-k_flows command to identify bottlenecks in a large organization’s network. The resulting report can guide further optimization efforts.

🔌 Integration with MCP Clients

The following AI applications are compatible with the ntopng MCP Server:

• Claude Desktop: Full support for MCP clients.
• Continue: Support limited to data tools and APIs, not full prompts.
• Cursor: Limited support, focusing on network tool integration rather than complete prompt functionality.

📊 Performance & Compatibility Matrix

The following table outlines the compatibility of the ntopng MCP Server with different MCP clients:

MCP Client	Resources	Tools	Prompts
Claude Desktop	✅	✅	✅
Continue	✅	✅	✅
Cursor	❌	✅	❌

🛠️ Advanced Configuration & Security

Configuring the MCP Server

The configuration of the ntopng MCP Server is crucial for secure and efficient operation. Below is an example JSON snippet:

{
  "mcpServers": {
    "ntopng_mcp_server": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-ntopng"],
      "env": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

Security Considerations

Ensure that your environment variables are securely managed and not exposed. Use environment variable secrets management tools like Vault or HashiCorp Secrets to handle sensitive information.

❓ Frequently Asked Questions (FAQ)

1. Q: How can I ensure compatibility with different MCP clients? A: The ntopng MCP Server supports a range of AI applications, ensuring broad compatibility across various use cases.

2. Q: Can this server be used for real-time network monitoring? A: Yes, the ntopng MCP Server can be configured to stream real-time data, making it suitable for continuous monitoring and analysis.

3. Q: How do I update the protocol flow in case of new ntopng versions? A: Keep your claude_desktop_config.json file updated with the latest version details and ensure that all dependencies are compatible with ntopng.

4. Q: Are there performance trade-offs when using this server for large-scale implementations? A: For large-scale deployments, consider optimizing query performance by fine-tuning database queries and configuring caching mechanisms.

5. Q: How can I troubleshoot issues with the MCP Server not connecting to ntopng? A: Check environment variables and network connectivity. Use logging and debug mode in uv to identify any connection or configuration errors.

👨‍💻Development & Contribution Guidelines

Contributions are welcome from developers who are passionate about integrating AI applications with network monitoring tools. To contribute, follow these steps:

1. Fork the Repository: Clone the repository and fork it on GitHub.
2. Set Up the Development Environment:
   • Install Node.js and npm
   • Run npm install to install dependencies
3. Run Tests:
   • Write tests for new features or improvements
   • Ensure all existing tests pass using npm test
4. Commit & Push Changes: Create a pull request after testing your changes.
5. Documentation Updates: Document any new features or important updates.

🌐 MCP Ecosystem & Resources

For more information on the Model Context Protocol and its ecosystem, visit the official documentation and community forums:

• ModelContextProtocol.org
• GitHub Repository

The ntopng MCP Server is a powerful tool for integrating AI applications with network monitoring data. Its comprehensive feature set and compatibility ensure that it is well-suited for a wide range of use cases in the AI workflow.

This documentation aims to provide clear guidance on setting up, configuring, and optimizing the ntopng MCP Server for seamless integration with various AI applications.