Kubernetes

prompt to build a mcp server: build a kubernet mcp server with top 30 kubernetes tools using the jlowin-fastmcp-8a5edab282632443.txt file. Make the functions dynamic so that it works for all cases even when the user does not provide a namespace or resource name.

The MCP server exposes the following Kubernetes operations as MCP tools:

- Pod Management: List, describe, and get logs for pods
- Deployment Management: List, scale, and inspect deployments
- Service Management: List and get details of services
- Namespace Management: List, create, and delete namespaces
- Node Management: List and describe nodes
- ConfigMap & Secret Management: List and get ConfigMaps and Secrets
- Persistent Volumes & Claims: List PVs and PVCs, get PVC details
- Job & CronJob Management: List and get jobs and cronjobs
- Ingress Management: List and get ingresses
- DaemonSet, StatefulSet, ReplicaSet Management: List and get details for each
- Event Management: List and get cluster events

All tools support filtering by namespace where applicable.

Ensurepythonandfastmcpare in your system PATH.

Install and configurekubectland connect to your cluster.

(Optional) Update yourmcp.jsonto add the MCP server endpoint:

"kubernetes-local": { "name": "Kubernetes MCP Server", "url": "http://localhost:8000/mcp/" }

The server will run onhttp://0.0.0.0:8000/mcp/by default.

You can now interact with your Kubernetes cluster using MCP tools (e.g., via GitHub Copilot or any MCP client).

- list_pods(namespace=None)
- get_pod_logs(pod_name=None, namespace=None)
- describe_pod(pod_name=None, namespace=None)
- list_deployments(namespace=None)
- scale_deployment(deployment_name, replicas, namespace)
- list_services(namespace=None)
- get_service(service_name=None, namespace=None)
- list_namespaces()
- create_namespace(namespace)
- delete_namespace(namespace)
- list_nodes()
- describe_node(node_name=None)
- list_configmaps(namespace=None)
- get_configmap(configmap_name=None, namespace=None)
- list_secrets(namespace=None)
- get_secret(secret_name=None, namespace=None)
- list_persistent_volumes()
- list_persistent_volume_claims(namespace=None)
- get_pvc(pvc_name=None, namespace=None)
- list_jobs(namespace=None)
- get_job(job_name=None, namespace=None)
- list_cronjobs(namespace=None)
- get_cronjob(cronjob_name=None, namespace=None)
- list_ingresses(namespace=None)
- get_ingress(ingress_name=None, namespace=None)
- list_daemonsets(namespace=None)
- get_daemonset(daemonset_name=None, namespace=None)
- list_statefulsets(namespace=None)
- get_statefulset(statefulset_name=None, namespace=None)
- list_events(namespace=None)
- get_event(event_name=None, namespace=None)
- list_replicasets(namespace=None)
- get_replicaset(replicaset_name=None, namespace=None)
- get me the pods running on the vp1099 namespace.
- scale down all pods in the vp1099 namespace to 1 replica.

- The server will attempt to use your local kubeconfig, or fall back to in-cluster config if running inside a cluster.
- Make sure yourkubectlcontext is set to the desired cluster/namespace.
- You can extend the server by adding more MCP tools using the@mcp.tooldecorator.
- Gitingest support:You can use gitingest to ingest and interact with GitHub repositories directly through MCP, enabling advanced code search and automation workflows alongside your Kubernetes operations.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An agent for automatically installing Kubernetes in a Rocky Linux environment using MCP.

Run and interpret Kubernetes commands interactively with a provided kubeconfig.

Inspect and debug Kubernetes clusters with read-only access to resources, CRDs, and pod logs.

Kubernetes-native registry for managing multiple MCP servers with lazy loading, health monitoring, and RBAC

Query and interact with kubernetes environments monitored by Metoro

Enables AI assistants to interact with Azure Kubernetes Service (AKS) clusters.

An MCP server for managing Kubernetes clusters, configured via an external JSON file.

Manage Kubernetes applications safely by creating and updating Cyclops Modules for AI agents.

A server for Kubernetes CLI tools like kubectl, istioctl, helm, and argocd, supporting multi-cluster management via dynamic kubeconfig.