Product Documentation
ADC
14.1-Current Release 13.1
View PDF

AI capabilities

June 19, 2026
Contributed by: 
C

NetScaler® AI capabilities extend the platform’s core application delivery and security functions to address the specific demands of AI workloads. As organizations deploy large language models (LLMs) and AI agents at scale, they face challenges that standard application gateways are not designed to handle, such as token-based traffic patterns, prompt governance, and agent tool access.

NetScaler addresses these challenges through four components:

  • AI Gateway manages and governs traffic between applications and LLM backends.
  • AI Gateway for Kubernetes extends AI Gateway capabilities into Kubernetes environments using the Gateway API.
  • MCP Gateway secures and controls traffic between AI agents and external MCP servers.
  • NetScaler Console MCP Server exposes NetScaler operational data to AI agents through MCP.

AI Gateway

AI Gateway acts as a centralized control plane between applications and AI model backends, such as Azure OpenAI and OpenAI. It introduces token awareness into the NetScaler routing and policy engine, understanding prompt size, response volume, and token generation rate, and applies that understanding to load balancing, rate limiting, governance, and observability decisions.

For more information, see AI Gateway.

AI Gateway for Kubernetes

AI Gateway for Kubernetes extends the same token-aware traffic management, governance, and observability capabilities to AI workloads running in Kubernetes environments. It uses the Kubernetes Gateway API, enabling platform and infrastructure teams to govern how applications access large language models through declarative, Kubernetes-native configuration, without modifying application code or building custom integration logic.

Standard Kubernetes ingress and gateway configurations treat all requests as equivalent. AI workloads are not: a single prompt can consume a handful of tokens or hundreds of thousands, making request-count controls an inaccurate proxy for resource usage, cost, or backend load. AI Gateway for Kubernetes addresses this by introducing token awareness into the Kubernetes data plane.

MCP Gateway

Model Context Protocol (MCP) is the protocol used by AI agents to interact with external tools and data sources, such as code repositories, databases, internal APIs, and SaaS platforms. Each MCP server exposes a set of tools that an agent can invoke to complete tasks.

MCP Gateway sits between AI agents and the MCP servers that they connect to, providing a centralized point to enforce access control, apply rate limits, monitor tool usage, and manage authentication. This gives security and infrastructure teams the same level of visibility and control over agent-to-tool traffic that AI Gateway provides over application-to-model traffic.

For more information, see MCP Gateway.

NetScaler Console MCP Server

While AI Gateway and MCP Gateway govern how AI workloads access external models and tools, the NetScaler Console MCP Server operates in the other direction. It makes NetScaler itself consumable by AI agents.

The NetScaler Console MCP Server is a remote MCP server that acts as an adapter between MCP-compatible AI clients and NetScaler Console. It exposes selected NetScaler Console capabilities as structured MCP tools, giving AI agents governed, well-defined access to NetScaler operational data without requiring custom integrations.

For more information, see NetScaler Console MCP Server.

AI Gateway is a rapidly evolving space, and we are continuously expanding our capabilities and integrations. Visit this section regularly for the latest updates and new features.

AI capabilities
June 19, 2026
Contributed by: 
C
June 19, 2026
Contributed by: 
C

In this article

Site feedback | Your privacy choices footer linkYour Privacy Choices | Privacy and legal terms | Cookie preferences | Consent settings | docs.cloud.com
© 1999- Cloud Software Group, Inc. All rights reserved.