For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Deploy an MCP server to a Kubernetes cluster with Solo Enterprise for kagent.

Before you begin

1. Follow the Solo Enterprise for kagent quickstart to set up Solo Enterprise for agentregistry and connect Solo Enterprise for kagent as a runtime.
2. Create an MCP server.
3. Build the Docker container image and push it to a container registry that your cluster can pull from.
4. Publish the MCP server to the catalog.
5. Port-forward the Solo Enterprise for agentregistry service on your local machine.

   kubectl -n agentregistry-system port-forward svc/agentregistry-enterprise-server 12121:12121

Deploy the MCP server

1. List the runtimes that are connected to Solo Enterprise for agentregistry and note the name of the runtime that you want to deploy your MCP server to. In the following example, the runtime name is kagent.

   arctl get runtimes

   Example output:

   NAME     TYPE
   kagent   Kagent
   

2. Create a Deployment for the MCP server. The registry spins up a Kubernetes pod for your MCP server from the Docker image reference that is stored in the registry catalog.

   arctl apply -f - <<EOF
   apiVersion: ar.dev/v1alpha1
   kind: Deployment
   metadata:
     name: mymcp
   spec:
     targetRef:
       kind: MCPServer
       name: mymcp
       tag: "latest"
     runtimeRef:
       kind: Runtime
       name: kagent
   EOF

   Example output:

   ✓ Deployment/mymcp created
   

3. Check the MCP server deployment in your cluster and make sure that the pod is up and running.

   kubectl get pods -n kagent | grep mymcp

   Example output:

   myorg-mymcp-5b695845df-vwbqn   1/1     Running   0   14s
   

4. Open the Instances view in the UI and select the MCP server that you deployed. You can monitor the progress of the deployment in the Instance Logs section.