What can you do with this server?

*This server provides a comprehensive interface for managing and monitoring Kubernetes and OpenShift clusters across various cloud providers. * Resource Management: List and inspect core cluster components including namespaces, pods, deployments, services, nodes, and events. * Deployment Control: Apply YAML manifests, scale deployments, and execute deployment rollouts or rollbacks (confirmation-gated). * Diagnostics: Access read-only tools to check pod health, view container logs, and examine cluster status. * Cluster Connectivity: Manage sessions and authentication using Kubeconfig files or in-cluster service accounts. * Safety Controls: Restrict dangerous operations (like deleting a pod or changing deployments) requiring explicit user confirmation.

Which integrations are available for this server?

Provides tools for interacting with Kubernetes clusters, including listing namespaces, pods, deployments, services, and nodes, reading pod logs and events, scaling and restarting Deployments, deleting pods, and applying Deployment or ConfigMap manifests.

How do I use k8s-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@k8s-mcp list all pods in the default namespace" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

k8s-cloud-deploy-mcp

MCP server owned by Pawan Gunjkar (pawangunjkar@gmail.com · GitHub). MIT licensed.

The server targets standard Kubernetes, Red Hat OpenShift, and cloud-managed clusters (AWS EKS, Azure AKS, GCP GKE). It loads a kubeconfig context or an in-cluster service account, detects OpenShift from apps.openshift.io/v1 or route.openshift.io, and reads CLOUD_PROVIDER, AWS_REGION, AZURE_SUBSCRIPTION_ID, GCP_PROJECT, and K8S_CONTEXT.

Read-only diagnostics run without a second confirmation. k8s_trigger_deployment_rollout and k8s_rollback_deployment return a plan until the caller sets confirm=true after the user approves it. Image updates must be sha256 digests. The tag latest is rejected. Secret values are never returned.

Project information

Item	Value
Package	`k8s-cloud-deploy-mcp`
Command	`k8s-cloud-deploy-mcp`
Runtime	Python 3.10+, FastMCP, official Kubernetes client, httpx, pydantic
Auth	`KUBECONFIG`, `K8S_CONTEXT`, or in-cluster service account
Providers	`aws_eks`, `azure_aks`, `gcp_gke`, `openshift`, `generic_k8s`

Related MCP server: MCP Server Kubernetes

Architecture

flowchart TB
  subgraph L1["Editor"]
    IDE["Cursor, Claude Code, or VS Code"]
  end
  subgraph L2["MCP"]
    SRV["k8s-cloud-deploy-mcp"]
    HUB["K8sHub session"]
  end
  subgraph L3["Cluster"]
    CFG["kubeconfig or in-cluster"]
    API["Kubernetes or OpenShift API"]
  end
  IDE --> SRV --> HUB --> CFG --> API

kubectl and oc are optional. The Python client is authoritative. Those binaries run only for client version and a short rollout-status check, with shell=False and a fixed argument list.

Environment

Variable	Role
`KUBECONFIG`	Kubeconfig file or path list
`K8S_CONTEXT`	Context name
`K8S_NAMESPACE`	Default namespace
`CLOUD_PROVIDER`	`aws_eks`, `azure_aks`, `gcp_gke`, `openshift`, or `generic_k8s`
`AWS_REGION`	Required with `aws_eks`
`AZURE_SUBSCRIPTION_ID`	Required with `azure_aks`
`GCP_PROJECT`	Required with `gcp_gke`

Prepare the kubeconfig with aws eks update-kubeconfig, az aks get-credentials, gcloud container clusters get-credentials, or oc login before starting the server.

Tools

Read-only: k8s_get_cluster_overview, k8s_list_deployments_and_configs, k8s_get_pod_health_and_diagnostics, k8s_get_container_logs, k8s_manage_openshift_routes_and_services, k8s_check_rollout_status.

Confirmation-gated writes: k8s_trigger_deployment_rollout, k8s_rollback_deployment. Pod delete still requires confirm=true.

The Agensi skill playbook is agensi_build/k8s-cloud-deploy-mcp-pro/SKILL.md.

Cursor

{
  "mcpServers": {
    "k8s-cloud-deploy-mcp": {
      "command": "uvx",
      "args": ["--from", "C:/AI_Workspaces/Anti_Workspace/k8s-mcp", "k8s-cloud-deploy-mcp"],
      "env": {
        "KUBECONFIG": "C:/Users/you/.kube/config",
        "K8S_CONTEXT": "dev",
        "CLOUD_PROVIDER": "generic_k8s"
      }
    }
  }
}

Agensi package

python scripts/build_agensi_zip.py

The scanner writes these files under dist/:

File	Contents
`k8s-cloud-deploy-mcp-pro.zip`	Agensi skill upload
`k8s-cloud-deploy-mcp-pro.tar.gz`	Same skill as a tar archive
`k8s_cloud_deploy_mcp-1.1.0.tar.gz`	Python source distribution
`k8s_cloud_deploy_mcp-1.1.0-py3-none-any.whl`	Python wheel

Upload the zip to agensi.io/dashboard/submit. Install the wheel with pip install dist/k8s_cloud_deploy_mcp-1.1.0-py3-none-any.whl.

Available Tools

15 tools

k8s_applyB

Create or patch a Deployment or ConfigMap from YAML.

Inputs: manifest_yaml (required), session_name. Returns: result

k8s_connectC

Load a kubeconfig context, or in-cluster config when no kubeconfig is available.

Inputs: context, namespace, kubeconfig, session_name. Returns: result

k8s_delete_podB

Delete one pod so the controller recreates it. confirm=true is required.

Inputs: pod (required), confirm, namespace, session_name. Returns: result

k8s_disconnectC

Drop a Kubernetes session.

Inputs: session_name. Returns: result

k8s_eventsA

Show the latest 30 namespaced events.

Inputs: namespace, session_name. Returns: result

k8s_list_deploymentsB

List deployments and ready replica counts.

Inputs: namespace, session_name. Returns: result

k8s_list_namespacesB

List namespace names.

Inputs: session_name. Returns: result

k8s_list_nodesB

List nodes and Ready condition.

Inputs: session_name. Returns: result

k8s_list_podsB

List pods with phase, ready count, and node.

Inputs: label, namespace, session_name. Returns: result

k8s_list_secret_namesB

List Secret names only. Values are not returned.

Inputs: namespace, session_name. Returns: result

k8s_list_servicesB

List services, type, and cluster IP.

Inputs: namespace, session_name. Returns: result

k8s_pod_logsB

Read the tail of a pod log.

Inputs: pod (required), tail, container, namespace, +1 more. Returns: result

k8s_restartC

Roll a Deployment by setting restartedAt.

Inputs: name (required), namespace, session_name. Returns: result

k8s_scaleC

Scale a Deployment.

Inputs: name (required), replicas (required), namespace, session_name. Returns: result

k8s_statusB

List Kubernetes sessions.

Inputs: no named parameters. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.2/5.0

Scored 2026-09-24 07:45 across 15 tools

Disambiguation5/5

Each tool targets a distinct resource and action: connect/disconnect manage sessions, list_* covers different Kubernetes resources, and pod_logs/scale/restart/delete_pod/apply are specific operations. There is no meaningful overlap—even multiple pod-related tools are clearly differentiated by their verbs.

Naming Consistency4/5

All tools share the k8s_ prefix and generally follow a verb_noun pattern (list_namespaces, scale, delete_pod). Minor deviations exist: k8s_events and k8s_pod_logs omit the list/get verb, but the pattern is still predictable and readable.

Tool Count4/5

At 15 tools, the server sits at the upper bound of the typical well-scoped range. The breadth is justified by covering connection management plus a variety of Kubernetes resources and operations, though it feels slightly heavy for a single-purpose MCP server.

Completeness3/5

The server covers listing many resources, logs, events, scaling, restarting, and applying YAML, but lacks get operations for individual resources, delete for most resources (only pods), and any write operations for services, secrets, or namespaces. It is read-heavy with limited lifecycle coverage beyond Deployments.

Maintenance

ActivityMaintained

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

ProdHub Application Delivery
io.github.SwaDeshiTech
Deploy applications and manage governed Kubernetes preview spaces and capacity.
CI/CD & DevOps Cloud Platforms Observability
1
https://app.prodhub.in/mcp
OwnkubeA
io.ownkube
Deploy and run apps, workers, jobs, Postgres, and Valkey on Ownkube from your coding agent.
CI/CD & DevOps Networking & Infrastructure
1
https://app.ownkube.io/api/mcp
Stashbase
io.github.stashbase
Secrets for developers and agents—secure context and workflows without exposing secret values.
Security Developer Tools
1
https://api.stashbase.dev/mcp
AnkraB
ai.ankra
Deploy and operate Kubernetes: clusters, stacks, apps, logs, metrics and security, with OAuth.
Agent Orchestration App Automation Networking & Infrastructure
5751
https://platform.ankra.app/api/v1/mcp

Related MCP Servers

Kubernetes MCP Server
Cloud Platforms Developer Tools OS Automation
thekaranpargaie
A
license
B
quality
D
maintenance
Enables managing Kubernetes clusters through natural language by providing tools to list resources, view logs, port-forward services, scale deployments, and execute kubectl operations via AI assistants.
Updated a year ago (2025-11-28 05:31 UTC)
81
MIT
MCP Server Kubernetes
Cloud Platforms Developer Tools Virtualization
Abinesh0206
A
license
Not graded
quality
D
maintenance
Enables comprehensive Kubernetes cluster management through kubectl operations, Helm chart deployments, pod troubleshooting, and node management. Supports both read-only and full cluster administration capabilities with built-in safety features.
Updated a year ago (2025-10-03 05:41 UTC)
11,892 npm
MIT
MCP Server Kubernetes
Cloud Platforms Virtualization Developer Tools
yasir27uk
A
license
C
quality
D
maintenance
Enables connecting to a Kubernetes cluster to manage resources and troubleshoot workloads with kubectl and Helm operations, including logs, scaling, port forwarding, and non-destructive mode.
Updated a month ago (2026-09-27 10:35 UTC)
22
11,892 npm
MIT
mcp-server-kubernetes
Cloud Platforms Virtualization Developer Tools
ACRT-EVAL
A
license
B
quality
D
maintenance
Enables connection to a Kubernetes cluster to list and manage pods, services, deployments, and nodes, create/delete/describe pods, inspect namespaces, and retrieve logs for debugging.
Updated 18 days ago (2026-10-24 04:01 UTC)
11
11,892 npm
MIT

k8s-cloud-deploy-mcp

Project information

Architecture

Environment

Tools

Cursor

Agensi package

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Kubernetes MCP Server

MCP Server Kubernetes

MCP Server Kubernetes

mcp-server-kubernetes