Kubernetes MCP Server

List Namespaces

List all namespaces in the Kubernetes cluster. Namespaces provide logical isolation for cluster resources. Use this to discover available namespaces, understand cluster organization, and identify where resources are deployed.

Get Namespace

Retrieve detailed information about a specific namespace. Returns namespace metadata, labels, annotations, status, and resource quotas. Use this to inspect namespace configuration and understand its properties.

Create Namespace

Create a new namespace in the cluster. Namespaces provide logical isolation and resource organization. You can specify labels and annotations for categorization and metadata. Use this to create new environments or separate application workloads.

List Pods

List all pods in a namespace or across all namespaces. Returns pod status, node assignment, container restarts, and age. Use this to monitor running applications, troubleshoot issues, identify failing pods, or get an overview of cluster workloads. Supports filtering by labels for targeted queries.

Get Pod

Retrieve detailed information about a specific pod. Returns complete pod specification, status, container details, volumes, environment variables, resource limits, and current conditions. Use this to debug pod issues, inspect configuration, or verify deployment specifications.

Create Pod

Create a new pod from a complete pod specification. Provide the full pod manifest including containers, volumes, labels, and other configuration. Use this to deploy standalone pods or test container images. For production workloads, consider using deployments instead.

Delete Pod

Delete a pod from the cluster. The pod will be terminated gracefully with a grace period (default 30 seconds). Use this to remove failed pods, restart problematic containers, or clean up test pods. Note that pods managed by deployments will be automatically recreated.

Get Pod Logs

Retrieve logs from a container in a pod. Essential for debugging application issues, monitoring behavior, analyzing errors, and troubleshooting crashes. Supports tailing recent lines, including timestamps, and accessing previous container logs (if the container restarted). For multi-container pods, specify the container name.

List Deployments

List all deployments in a namespace or across all namespaces. Deployments manage replica sets and provide declarative updates for pods. Returns deployment status, replica counts (desired/current/ready), and update strategy. Use this to monitor application deployments, check rollout status, and identify scaling issues.

Get Deployment

Retrieve detailed information about a specific deployment. Returns complete deployment specification, status, replica counts, conditions, update strategy, pod template, and rollout history. Use this to inspect deployment configuration, troubleshoot failed rollouts, or verify deployment settings.

Create Deployment

Create a new deployment from a complete deployment specification. Deployments manage replica sets and provide declarative updates for pods with rolling update capabilities. Provide the full deployment manifest including replica count, pod template, selectors, and update strategy. Use this to deploy applications with automated rollout management.

Update Deployment

Update an existing deployment by patching specific fields. Use JSON Patch, Merge Patch, or Strategic Merge Patch to modify deployment configuration such as image version, replica count, environment variables, or resource limits. This triggers a rolling update of the pods. Use this for application updates, configuration changes, or adjusting deployment parameters.

Scale Deployment

Scale a deployment by modifying the replica count. Increases or decreases the number of pod replicas to handle load changes, scale horizontally, or reduce resource usage. Use this for manual scaling operations, handling traffic spikes, or scaling down during maintenance. The change triggers a gradual rollout based on the update strategy.

Delete Deployment

Delete a deployment from the cluster. This removes the deployment and all associated replica sets and pods. Pods are terminated gracefully with their configured grace period. Use this to remove applications, clean up test deployments, or decommission services. Be cautious as this is a destructive operation that will take down the application.

List Services

List all services in a namespace or across all namespaces. Services provide stable network endpoints and load balancing for pods. Returns service type (ClusterIP, NodePort, LoadBalancer), cluster IP, ports, and selectors. Use this to discover available services, understand service networking, and troubleshoot connectivity issues.

Get Service

Retrieve detailed information about a specific service. Returns complete service specification including type, cluster IP, external IPs, ports, selectors, session affinity, and endpoint information. Use this to inspect service configuration, troubleshoot routing issues, or verify load balancing settings.

Create Service

Create a new service to expose pods as a network service. Services provide stable endpoints and load balancing across pods matching the selector. Specify service type (ClusterIP for internal, NodePort for node-level access, or LoadBalancer for external access), ports, and pod selectors. Use this to expose applications internally or externally.

List Ingresses

List all ingress resources in a namespace or across all namespaces. Ingresses manage external HTTP/HTTPS access to services, providing load balancing, SSL termination, and name-based virtual hosting. Returns ingress rules, hosts, paths, and backend services. Use this to understand external routing configuration and troubleshoot ingress issues.

List ConfigMaps

List all ConfigMaps in a namespace. ConfigMaps store non-confidential configuration data as key-value pairs that can be consumed by pods as environment variables, command-line arguments, or configuration files. Use this to discover available configurations, audit config usage, or identify configuration resources.

Get ConfigMap

Retrieve detailed information about a specific ConfigMap. Returns all key-value pairs stored in the ConfigMap along with metadata. Use this to inspect configuration values, verify settings, or extract configuration data for analysis. ConfigMaps store non-sensitive data like application settings, feature flags, or configuration files.

List Secrets

List all secrets in a namespace. Secrets store sensitive data like passwords, tokens, SSH keys, and TLS certificates. Returns secret names, types, and metadata (but not the actual secret values). Use this to discover available secrets, audit secret usage, or identify credential resources. To view secret values, use the Get Secret tool.

Get Secret

Retrieve detailed information about a specific secret including its base64-encoded values. Secrets store sensitive data like passwords, API tokens, TLS certificates, and SSH keys. Returns all key-value pairs with base64-encoded values. Use this carefully to inspect credentials, extract certificates, or verify secret contents. Remember to decode base64 values to get the actual data.

List Jobs

List all batch jobs in a namespace. Jobs create one or more pods and ensure they successfully complete. Returns job status, completions, duration, and active pods. Use this to monitor batch processing, check job completion status, troubleshoot failed jobs, or track data processing tasks.

Get Job

Retrieve detailed information about a specific job. Returns complete job specification, status, completion time, pod template, parallelism settings, and failure conditions. Use this to inspect job configuration, understand job failures, check completion status, or troubleshoot batch processing issues.

List CronJobs

List all CronJobs in a namespace. CronJobs create jobs on a scheduled basis using cron syntax (similar to Unix cron). Returns schedule, last schedule time, active jobs, and job history. Use this to monitor scheduled tasks, verify cron schedules, check job execution history, or troubleshoot scheduled batch processing.

List Nodes

List all nodes in the Kubernetes cluster. Nodes are the worker machines (VMs or physical servers) that run containerized applications. Returns node status, capacity (CPU, memory, pods), allocatable resources, conditions, and Kubernetes version. Use this to monitor cluster capacity, check node health, identify resource availability, or troubleshoot scheduling issues.

Get Node

Retrieve detailed information about a specific node. Returns complete node specification including capacity, allocatable resources, conditions (Ready, MemoryPressure, DiskPressure), system info (OS, kernel, container runtime), addresses, and taints. Use this to inspect node configuration, troubleshoot node issues, verify resource availability, or check node labels and taints.

List Events

List cluster events for debugging and monitoring. Events are generated by the Kubernetes control plane to report what's happening in the cluster - pod scheduling, container failures, resource issues, etc. Can be scoped to a specific namespace or cluster-wide. Returns event type, reason, message, and involved objects. Use this to troubleshoot issues, understand cluster activity, investigate pod failures, or monitor system behavior.