AWS Bedrock AgentCore

Deploy an agent from the Solo Enterprise for agentregistry catalog to AWS Bedrock AgentCore.

Before you begin

Follow the AWS Bedrock AgentCore quickstart guide to install Solo Enterprise for agentregistry, deploy a managed EC2 gateway, and register the AWS Bedrock AgentCore runtime. Make sure that the following networking details are stored in environment variables:
```
echo $SUBNET_IDS_YAML
echo $SG_ID
echo $AWS_REGION
```
Create an agent.
Store the agent code in a GitHub repository.
Note
For testing purposes, you can skip this step and use the example agent in Solo.io’s sample repo instead, https://github.com/solo-io/exampleagent.
Publish the agent to the catalog.
Port-forward the Solo Enterprise for agentregistry service on your local machine so that you can interact with the registry.
```
kubectl -n agentregistry-system port-forward svc/agentregistry-enterprise-server 12121:12121
```

Deploy the agent

Open the agent catalog in the Solo Enterprise for agentregistry UI and select the agent that you want to deploy.
Click Deploy to open the deployment wizard.
Select the provider and region that you want to deploy your agent to. Then, click Deploy Agent.
Monitor the progress of the deployment in the Instance Logs section of your agent deployment. Note that the deployment can take a few minutes to complete.

List the runtimes that are connected to Solo Enterprise for agentregistry and note the name of the runtime that you want to deploy your agent to. In the following example, the runtime name is agentcore.
```
arctl get runtimes
```
Example output:
```
NAME                 TYPE
agentcore            BedrockAgentCore
kubernetes-default   kubernetes
local                local
```

Create a Deployment for the agent. The registry fetches the agent source code and Dockerfile from the GitHub URL that you provided when you published the agent to the registry catalog. Then, the registry packages the code and builds an image that is compatible to run on AWS Bedrock AgentCore, and uses that image to deploy the runtime inside your VPC. The deploymentRefs field links the agent to its MCP server deployment so that MCP tool calls are automatically routed through the gateway.

arctl apply -f - <<EOF
apiVersion: ar.dev/v1alpha1
kind: Deployment
metadata:
  name: myagent
spec:
  targetRef:
    kind: Agent
    name: myagent
    tag: "latest"
  runtimeRef:
    kind: Runtime
    name: agentcore
  deploymentRefs:
    - name: mymcp
  runtimeConfig:
    region: $AWS_REGION
    workdir: agentregistry/myagentmcp
    networkMode: vpc
    subnetIds:
${SUBNET_IDS_YAML}
    securityGroupIds:
      - ${SG_ID}
EOF

Setting	Description
`targetRef`	The agent that you want to deploy.
`runtimeRef`	The name of the runtime to deploy to.
`deploymentRefs`	Links the agent deployment to its MCP server deployment. The registry uses this to wire the MCP server’s gateway backend into the agent so that MCP tool calls are routed through the gateway.
`runtimeConfig.region`	The AWS region to deploy to.
`runtimeConfig.workdir`	The subdirectory within the repository that contains the agent’s source code and Dockerfile.
`runtimeConfig.networkMode`	Set to `vpc` to deploy the agent inside your private VPC. Required for the agent to reach the MCP server over the private network.
`runtimeConfig.subnetIds`	The private subnets in which the agent runtime is deployed.
`runtimeConfig.securityGroupIds`	The security groups applied to the agent runtime.

Example output:

✓ Deployment/myagent created

Open the Instances view in the UI and select the agent that you deployed. You can monitor the progress of the deployment in the Instance Logs section. Note that the deployment can take a few minutes to complete.

Chat with the agent

You can chat with the agent by using the Solo Enterprise for agentregistry or AWS Bedrock AgentCore UI.

Open the Instances view in the UI and select the myagent agent.
In the Agent Details card, click Open Chat.
Chat with the agent. For example, you can ask it what it can do for you. Then, hit Enter and wait for the agent to reply.

Open the AWS Bedrock AgentCore agents overview and select the agent that you deployed.
Go to the ENDPOINTS card, and click the Default endpoint.
Click Test endpoint to open the agent sandbox.
In the agent sandbox, make sure that your agent is selected from the Runtime drop down.

In the Input card, enter the following prompt and click Run. Verify that you get back an answer from your agent.

{
  "jsonrpc": "2.0",
  "id": "1",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "what can you do?"
        }
      ],
      "messageId": "msg-1",
      "contextId": "f5bd2a40-74b6-4f7a-b649-ea3f09890003"
    }
  }
}

Example output:

{
  "id": "1",
  "jsonrpc": "2.0",
  "result": {
     "artifacts": [
     {
         "artifactId": "11a1111a1-1a1a-1111-1a11-11a11aa11111",
         "parts": [
         {
             "kind": "text",
             "text": "I can roll dice of different sizes and check if numbers are prime. Just ask me to roll a die (specifying the number of sides) or ask me to check if a number is prime.\n"
         }
         ]
     }
...

Solo Enterprise for kagent