Quickly build a Q&A agent using kagent - Container Service for Kubernetes

This guide demonstrates how to deploy a Question & Answer (Q&A) agent using Kagent. The agent leverages the qwen3-coder-plus model from Alibaba Cloud Model Studio and a fetch Model Context Protocol (MCP) service to retrieve and summarize web page content in real time.

Preparations

Create a namespace named kagent in your ACK cluster.
Install the kagent-crds and kagent applications in the kagent namespace from the ACK Marketplace or using Applications > Helm.
Activate the Alibaba Cloud Model Studio and create an API key.

Step 1: Create a ModelConfig

Get the KubeConfig of your cluster and use kubectl to connect to the cluster. If your cluster does not have public network access enabled, you can use Workbench to connect to the cluster over the internal network. On the Cluster Information page, click Manage Clusters Using Workbench in the upper-right corner.

Export your Model Studio API key as an environment variable and create a Secret in the kagent namespace.

export PROVIDER_API_KEY=${Your_Model_Studio_API_Key}
kubectl create secret generic bailian-apikey -n kagent --from-literal credential="$PROVIDER_API_KEY"

Apply the following YAML to create the ModelConfig resource. The provider is set to OpenAI because Model Studio exposes an OpenAI-compatible API.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
  name: bailian-provider-config
spec:
  model: qwen3-coder-plus
  apiKeySecret: bailian-apikey
  apiKeySecretKey: credential
  openAI:
    baseUrl: https://dashscope-intl.aliyuncs.com/compatible-mode/v1
  provider: OpenAI
EOF

Step 2: Deploy the `fetch` MCP server

Deploy the fetch MCP server in your ACK cluster.

kubectl -n kagent apply -f - <<EOF
apiVersion: apps/v1
kind: Deployment
metadata:
  name: streamablehttp-fetch-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: streamablehttp-fetch
  template:
    metadata:
      labels:
        app: streamablehttp-fetch
    spec:
      containers:
      - name: streamablehttp-fetch-container
        image: registry-cn-hangzhou.ack.aliyuncs.com/dev/streamablehttp-fetch:latest
---
apiVersion: v1
kind: Service
metadata:
  name: streamablehttp-fetch-service
spec:
  selector:
    app: streamablehttp-fetch
  ports:
    - protocol: TCP
      port: 3000
      targetPort: 3000
  type: ClusterIP
EOF

Step 3: Register the MCP Server

Create the RemoteMCPServer resource to register the fetch service with Kagent. This tells the system how to communicate with the MCP server deployed in the previous step.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: RemoteMCPServer
metadata:
  name: streamablehttp-fetch
spec:
  description: A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to Markdown for easier consumption.
  protocol: STREAMABLE_HTTP
  sseReadTimeout: 5m0s
  terminateOnClose: true
  timeout: 30s
  url: http://streamablehttp-fetch-service:3000/
EOF

Verify that the MCP server is successfully registered and accepted.

kubectl get RemoteMCPServer -n kagent

Expected output:

NAME                   PROTOCOL          URL                                        ACCEPTED
streamablehttp-fetch   STREAMABLE_HTTP   http://streamablehttp-fetch-service:3000/   True

Step 4: Create the agent

Apply the Agent configuration.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: Agent
metadata:
  name: gateway-api-professor
  namespace: kagent
spec:
  declarative:
    modelConfig: bailian-provider-config
    stream: true
    systemMessage: |-
      You are a friendly and helpful agent. Use the streamablehttp-fetch tool to get GatewayAPI information from the following URLs to answer user questions about GatewayAPI.
      
      # Links
      - intro: https://gateway-api.sigs.k8s.io/
      - api-overview: https://gateway-api.sigs.k8s.io/concepts/api-overview/
      - use-case: https://gateway-api.sigs.k8s.io/concepts/use-cases/
      - servicemesh: https://gateway-api.sigs.k8s.io/mesh/
      - implementations: https://gateway-api.sigs.k8s.io/implementations/
      - v1.4 support overview: https://gateway-api.sigs.k8s.io/implementations/v1.4/
      - Full spec, large page: https://gateway-api.sigs.k8s.io/reference/spec/

      # Instructions

      - If a user's question is unclear, ask for clarification before running any tools.
      - Be friendly and enthusiastic in your responses to the user.
      - If you do not know how to answer a question, do not make up an answer.
        Reply with "Sorry, I don't know how to answer that question" and ask the user to clarify.
      - If the user asks for a summary or an overview, make sure to read the entire text before answering.

      # Response format
      - Always reply in Markdown format.
      - Your response must include a summary of the actions you performed and an explanation of the results.
    tools:
    - type: McpServer
      mcpServer:
        apiGroup: kagent.dev
        kind: RemoteMCPServer
        name: streamablehttp-fetch
        toolNames:
        - fetch
  description: This agent primarily answers questions related to the GatewayAPI specification.
  type: Declarative
EOF

Verify that the agent and dependent components are running.

kubectl get pod -n kagent