This article provides an overview of Kentik’s AI Advisor MCP Server , which lets you integrate AI Advisor into external AI agents.
Note: If you have an Infoblox account and a Kentik account, you can ask questions about your Infoblox data directly from AI Advisor chats (requires Kentik administrator setup, see Infoblox Integration).
What Is MCP?
The Model Context Protocol (MCP) is an industry standard for AI agents to access data and interact with external systems. It's supported by major AI platforms including:
Claude Desktop (Anthropic)
Custom AI agent frameworks: LangGraph, Google ADK, LlamaIndex, etc.
Tip: Already familiar with MCP? Jump straight to Getting Started and start setting up
ai-advisor.
Key Features
This Kentik-hosted service provides a standardized interface for AI agents to query your network data and maintain conversational context.
Natural Language Queries: Lets you ask questions about your network in conversational language
Multi-Turn Conversations: Maintains context across multiple questions
Real-Time Progress: Shows AI Advisor's reasoning process as it works
Asynchronous Processing: Handles long-running queries efficiently
Session Management: Lets you review and continue previous conversations
Flexible Authentication: Lets you authenticate with OAuth or an API token
Use Cases
To get the most out of the AI Advisor MCP Server, tailor your prompts to specific operational goals. Here are a few NetOps-related examples:
Operational Goal | Example Prompt |
|---|---|
Health Monitoring | "Show me all devices with high CPU usage." |
Troubleshooting | "Check which interfaces have errors in the last hour." |
Traffic Analysis | "What is the traffic volume on my external interfaces?" |
Next Steps
To begin using Kentik’s AI Advisor MCP server, complete one or more of the following:
Follow the Getting Started guide to go over prerequisites.
Modify one of the Configuration Examples for your agent or environment of choice, using OAuth or an API token, and to connect the MCP server.
Study the additional background information in Kentik AI Advisor, Kentik AI Advisor API, and MCP Specification.