Tag: AI

INTRODUCTION

In the previous article, we started exploring the capabilities of Veeam Intelligence.

Today, we’ll take a look at its natural evolution: the Veeam MCP Server.

MCP – THE NEW AI STANDARD

MCP (Model Context Protocol) is an open-source standard developed in late 2024 by Anthropic to connect AI applications (agents/LLMs) to external systems and data using a client-server architecture.

The main components of the MCP architecture are:

• MCP Host: an AI application that coordinates and manages one or more MCP clients
• MCP Client: a component that maintains a connection with an MCP server and retrieves context from the MCP server so that the MCP host can use it
• MCP Server: a program that provides context to MCP clients

The MCP protocol consists of two layers:

• Data layer: defines the JSON-RPC-based protocol for client-server communication, including connection lifecycle management, server features such as tools, resources, and prompts, and finally client features and utilities such as messages and notifications
• Transport layer: defines the communication mechanisms and channels that enable client-server data exchange; the supported transport types are stdio and streamable http

MCP servers can be local, serving a single MCP client via the STDIO protocol, or remote, serving multiple MCP clients via the HTTP Streamable protocol.

VEEAM MCP SERVER

The release of the Veeam MCP Server enables the use of Veeam Intelligence via the MCP protocol, allowing AI clients (MCP-compatible) to interact with data and tools from Veeam installations.

Key benefits:

• real-time, cross-system information for operators and AI agents
• Centralized natural language conversational interface for supported operations
• Secure, read-only access to data from your Veeam infrastructure
• Comprehensive management of deployment, data exposure, and integration with AI clients

Currently, the Veeam products supported for interaction via the MCP Server are:

• Veeam Backup & Replication
• Veeam ONE
• Veeam Service Provider Console

By interacting with the Veeam MCP Server, the AI assistant can combine real-time data from your backup environment with the Veeam knowledge base to generate a specific and reliable response.

For example, you can request analyses of the status of backups, repositories, the overall health of the infrastructure, malware detection events, and much more.

For details on available features, please refer to the official link.

INSTALLATION & LAB

For this lab, it was used:

• Windows 11 client
• Docker Desktop with WSL2
• Visual Studio Code with the GitHub Copilot extension

Prerequisites: Docker or Node.js v24, Veeam license (not the Community Edition)

The setup of the Veeam MCP Server consists of the following main steps:

1 clone repository

2 build docker image

3 get MCP client config file info (product type, URL, Veeam Administrator credentials)

4 connect Github Copilot account to VS Code

5 setup MCP Client into VS Code

6 add MCP server

7 start MCP server

8 use Veeam Intelligence through the MCP Server in Github Copilot chat

VEEAM MCP SERVER – HTTP STREAMABLE

To enable remote access via the HTTP Streamable protocol for cloud-based agents or multiple users within your organization, you can use the Veeam Intelligence MCP Streamable Wrapper feature.

In this case, the “veeam-mcp-server” repository must be imported into the directory where the “veeam-intelligence-mcp-streamable” repository was downloaded.

Prerequisites: npm and Docker Compose

The setup for the Veeam MCP Server HTTP Streamable is similar to the previous one, but with a few differences:

1 clone repository

2 install dependencies (npm)

3 get MCP client config file info (product type, URL, Veeam Administrator credentials)

4 edit config.json file

5 start wrapper

6 connect Github Copilot account to VS Code

7 setup remote MCP Client into VS Code

8 add MCP server

9 start MCP server

10 use Veeam Intelligence through the MCP Server in remote Github Copilot chat

For details on this additional feature, please refer to the project’s GitHub page.

CONCLUSION

Using Veeam Intelligence, combined with the capabilities of the Veeam MCP server, allows you to fully leverage the potential of AI, with the ability to integrate agents that extend the workflow to other business processes, such as opening an incident on your ticketing portal in the event of backup alerts.

In short, the path to AI evolution is set; let’s get ready for many more innovations! 💚

INTRODUCTION

The topic of AI has now become a major part of our lives, and it is about to revolutionize the world of IT, hopefully in a positive way.

Veeam Software, a leader in data protection, has long been developing what has since been renamed Veeam Intelligence.

VEEAM INTELLIGENCE

It is essentially a Gen-AI chatbot, based on a private OpenAI’s GPT-4 and trained on data from Veeam’s technical documentation, Knowledge Base, and official R&D forums.

Thanks to this agent, integrated into the Veeam Data Platform, you can interact using natural language, speeding up manual tasks such as verifying backup results, analyzing alerts, and reviewing complex reports.

Veeam Intelligent is available in two configuration modes:

• Basic mode: allows you to ask general questions about the features of various Veeam software products or common issues
• Advanced mode: based on data from the user’s environment, it allows you to perform operations specific to that particular context, such as analyzing the backup infrastructure, customizing reports, or using targeted threat scan and ransomware detection techniques

In addition, you can interact with the AI assistant within the Help Center, the main access point to all official documentation.

The KB4539 article provides a detailed description of all the new features introduced over time in this functionality.

Veeam also provides a prompt library, which is still limited in content but is useful for those new to using Veeam Intelligence.

The application of AI in Veeam is not limited to this Gen-AI assistant; thanks to advanced machine learning techniques, it is also used for the constant monitoring and analysis of our data protection infrastructure, detecting anomalies and identifying suspicious activity before, during, and after a backup.

💡 Tip: Don’t forget to set up the “Morning Coffee Report”, a daily AI-generated report that summarizes backup sessions, highlights the most significant issues found, and provides helpful tips for resolving them!

CONCLUSION

In a world where technology is evolving at an exponential rate, the use of AI in data protection can definitely bring enormous benefits in terms of accuracy, operational reliability, and, of course, time savings, allowing for the optimization of “human intelligence” for higher-value activities.

P.S.: in the next article, we’ll explore the latest evolution of Veeam Intelligence: its integration with the MCP Protocol, an open standard developed by Anthropic to connect AI applications to external data and tools.

Enjoy! 💚