agentgateway

Configure agentgateway for AI backends, MCP routing, and traffic policies in Kubernetes.

2|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/totallyGreg/claude-mp --skill agentgateway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentgateway
Source: https://github.com/totallyGreg/claude-mp/tree/main/plugins/gateway-manager/skills/agentgateway
Command: npx skills add https://github.com/totallyGreg/claude-mp --skill agentgateway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Guides operators in configuring agentgateway for AI backends, MCP routing, external processing, and traffic policies within Kubernetes.

Core Features & Use Cases

  • Provides end-to-end guidance for setting up provider backends (OpenAI, Anthropic, Gemini, Vertex AI, Azure OpenAI, Bedrock), MCP server routing, and ExtProc integrations.
  • Includes best practices for Kubernetes Secrets, RBAC considerations, Helm lifecycle, and route/policy orchestration.
  • Offers troubleshooting patterns and reference materials to accelerate deployment and operations across multi-backend Gateways.

Quick Start

Configure a new agentgateway routing setup for a Kubernetes cluster.

Frequently Asked Questions about agentgateway

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure LLM routing for multiple backends in Kubernetes?

To configure LLM routing, set up provider backends like OpenAI, Anthropic, Gemini, and local Ollama, then apply route-level traffic policies using Helm lifecycle management within your Kubernetes cluster.

What is MCP routing and how does it work with AI gateways?

MCP routing directs traffic to MCP server endpoints, allowing Kubernetes gateways to orchestrate requests across multiple AI backends while enforcing route-level traffic policies and external processing.

Can I use agentgateway with local Ollama and cloud providers like Bedrock simultaneously?

Yes, agentgateway supports multi-backend setups across local Ollama, OpenAI, Anthropic, Gemini, Vertex AI, Azure OpenAI, and Bedrock simultaneously, applying unified route-level policies across all providers.

How do I handle Kubernetes Secrets and RBAC for AI gateway deployments?

Handle Kubernetes Secrets and RBAC for AI gateway deployments by following established best practices for secret handling and RBAC considerations to ensure secure provider backend authentication and policy orchestration.

Does ExtProc integration support traffic policies for multi-backend gateways?

Yes, ExtProc integration supports traffic policies for multi-backend gateways by enabling external processing alongside MCP routing and provider backend management within Kubernetes environments.

What are the Helm lifecycle best practices for deploying AI routing gateways?

Helm lifecycle best practices for deploying AI routing gateways involve managing provider backend configurations, MCP server endpoints, and route-level policies to ensure reliable multi-backend operations across Kubernetes clusters.