mcp

com.googleapis.container/mcpVersion 1.0.0

Provides read access to your GKE and Kubernetes resources.

Status

Responds48 msNov 14, 2026, 13:59 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 13:59 UTC
Latency: 48 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://container.googleapis.com/mcpResponds48 msNov 14, 2026, 13:59 UTC

No sign-in

Claude Code

claude mcp add --transport http container https://container.googleapis.com/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: container
Remote MCP server URL: https://container.googleapis.com/mcp

Cursor

{
  "mcpServers": {
    "container": {
      "url": "https://container.googleapis.com/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"container","type":"http","url":"https://container.googleapis.com/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

27 tools

Tools of mcp
	Description		Read-only	Idempotent	Open world
`apply_k8s_manifest`Applies a Kubernetes manifest to a cluster using server-side apply. This is similar to running `kubectl apply --server-side`.	Applies a Kubernetes manifest to a cluster using server-side apply. This is similar to running `kubectl apply --server-side`.	Yes	No	Yes	No
`cancel_operation`Cancels a specific GKE operation.	Cancels a specific GKE operation.	Yes	No	Yes	No
`check_k8s_auth`Checks whether an action is allowed on a Kubernetes resource. This is similar to running `kubectl auth can-i`.	Checks whether an action is allowed on a Kubernetes resource. This is similar to running `kubectl auth can-i`.	No	Yes	Yes	No
`create_cluster`Creates a new GKE cluster in a given project and location. It's recommended to read the [GKE documentation](https://docs.cloud.google.com/kubernetes-engine/docs/concepts/configuration-overview) to understand cluster configuration options. For regional locations, cluster creation will default to Autopilot mode, as recommended by GKE best practices. If the user explicitly wants to create a Standard cluster, you need to set autopilot.enabled=false in the cluster configuration. Clusters in zonal locations are always Standard clusters. If a Standard cluster configuration has neither nodePools nor initialNodeCount, the cluster is created without any nodes (older GKE versions reject the request), so include nodePools or initialNodeCount when the user needs nodes to run workloads. This is similar to running `gcloud container clusters create-auto` or `gcloud container clusters create`.	Creates a new GKE cluster in a given project and location. It's recommended to read the [GKE documentation](https://docs.cloud.google.com/kubernetes-engine/docs/concepts/configuration-overview) to understand cluster configuration options. For regional locations, cluster creation will default to Autopilot mode, as recommended by GKE best practices. If the user explicitly wants to create a Standard cluster, you need to set autopilot.enabled=false in the cluster configuration. Clusters in zonal locations are always Standard clusters. If a Standard cluster configuration has neither nodePools nor initialNodeCount, the cluster is created without any nodes (older GKE versions reject the request), so include nodePools or initialNodeCount when the user needs nodes to run workloads. This is similar to running `gcloud container clusters create-auto` or `gcloud container clusters create`.	No	No	No	No
`create_node_pool`Creates a node pool for a specific GKE cluster.	Creates a node pool for a specific GKE cluster.	No	No	No	No
`delete_k8s_resource`Deletes a Kubernetes resource from a cluster. This is similar to running `kubectl delete`.	Deletes a Kubernetes resource from a cluster. This is similar to running `kubectl delete`.	Yes	No	No	No
`describe_k8s_resource`Shows the details of a specific Kubernetes resource. This is similar to running `kubectl describe`.	Shows the details of a specific Kubernetes resource. This is similar to running `kubectl describe`.	No	Yes	Yes	No
`diagnose_k8s_workload`Collects a correlated incident snapshot for a Kubernetes workload (Deployment, StatefulSet, DaemonSet), verifying referenced ConfigMaps, Secrets, and PVCs, warning events, and automatically deduplicating container error logs.	Collects a correlated incident snapshot for a Kubernetes workload (Deployment, StatefulSet, DaemonSet), verifying referenced ConfigMaps, Secrets, and PVCs, warning events, and automatically deduplicating container error logs.	No	Yes	Yes	No
`get_cluster`Gets the details of a specific GKE cluster.	Gets the details of a specific GKE cluster.	No	Yes	Yes	No
`get_k8s_cluster_health`Computes a high-level health scorecard across nodes, workloads, system pods, and control-plane components (GKE cluster state, admission webhooks, and API Priority and Fairness).	Computes a high-level health scorecard across nodes, workloads, system pods, and control-plane components (GKE cluster state, admission webhooks, and API Priority and Fairness).	No	Yes	Yes	No
`get_k8s_cluster_info`Gets cluster endpoint information. This is similar to running `kubectl cluster-info`.	Gets cluster endpoint information. This is similar to running `kubectl cluster-info`.	No	Yes	Yes	No
`get_k8s_log_summary`Fetches and deduplicates container logs using pattern fingerprinting to reduce token usage. Prefer this over get_k8s_logs when triaging crashes or noisy logs.	Fetches and deduplicates container logs using pattern fingerprinting to reduce token usage. Prefer this over get_k8s_logs when triaging crashes or noisy logs.	No	Yes	Yes	No
`get_k8s_logs`Gets logs from a Kubernetes container in a pod. This is similar to running `kubectl logs`.	Gets logs from a Kubernetes container in a pod. This is similar to running `kubectl logs`.	No	Yes	Yes	No
`get_k8s_resource`Gets one or more Kubernetes resources from a cluster. Resources can be filtered by type, name, namespace, and label selectors. Returns the resources in YAML format. This is similar to running `kubectl get`.	Gets one or more Kubernetes resources from a cluster. Resources can be filtered by type, name, namespace, and label selectors. Returns the resources in YAML format. This is similar to running `kubectl get`.	No	Yes	Yes	No
`get_k8s_rollout_status`Checks the current rollout status of a Kubernetes resource. This is similar to running `kubectl rollout status`.	Checks the current rollout status of a Kubernetes resource. This is similar to running `kubectl rollout status`.	No	Yes	Yes	No
`get_k8s_version`Retrieves Kubernetes client and server versions for a given cluster. This is similar to running `kubectl version`.	Retrieves Kubernetes client and server versions for a given cluster. This is similar to running `kubectl version`.	No	Yes	Yes	No
`get_node_pool`Gets the details of a specific node pool within a GKE cluster.	Gets the details of a specific node pool within a GKE cluster.	No	Yes	Yes	No
`get_operation`Gets the details of a specific GKE operation.	Gets the details of a specific GKE operation.	No	Yes	Yes	No
`list_clusters`Lists GKE clusters in a given project and location. Location can be a region, zone, or '-' for all locations.	Lists GKE clusters in a given project and location. Location can be a region, zone, or '-' for all locations.	No	Yes	Yes	No
`list_k8s_api_resources`Retrieves the available API groups and resources from a Kubernetes cluster. This is similar to running `kubectl api-resources`.	Retrieves the available API groups and resources from a Kubernetes cluster. This is similar to running `kubectl api-resources`.	No	Yes	Yes	No
`list_k8s_cluster_issues`Scans a cluster or namespace for abnormal pods (CrashLoopBackOff, OOMKilled, ImagePullBackOff), node pressure, stalled rollouts, quota exhaustion, PDB blocks, admission webhook risks, and API Priority and Fairness issues.	Scans a cluster or namespace for abnormal pods (CrashLoopBackOff, OOMKilled, ImagePullBackOff), node pressure, stalled rollouts, quota exhaustion, PDB blocks, admission webhook risks, and API Priority and Fairness issues.	No	Yes	Yes	No
`list_k8s_events`Retrieves events from a Kubernetes cluster. This is similar to running `kubectl events`.	Retrieves events from a Kubernetes cluster. This is similar to running `kubectl events`.	No	Yes	Yes	No
`list_node_pools`Lists the node pools for a specific GKE cluster.	Lists the node pools for a specific GKE cluster.	No	Yes	Yes	No
`list_operations`Lists GKE operations in a given project and location. Location can be a region, zone, or '-' for all locations.	Lists GKE operations in a given project and location. Location can be a region, zone, or '-' for all locations.	No	Yes	Yes	No
`patch_k8s_resource`Patches a Kubernetes resource. This is similar to running `kubectl patch`.	Patches a Kubernetes resource. This is similar to running `kubectl patch`.	Yes	No	No	No
`update_cluster`Updates a specific GKE cluster.	Updates a specific GKE cluster.	Yes	No	Yes	No
`update_node_pool`Updates a specific node pool within a GKE cluster.	Updates a specific node pool within a GKE cluster.	Yes	No	Yes	No

Details

Registry status: Active
Published: Apr 19, 2026
Updated: Apr 19, 2026
Website: Not given
Repository: Not given
Categories (suggested): Cloud and infrastructureSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing