MCP server
Kubernetes MCP server
An open-source MCP server that lets AI read Kubernetes cluster state and logs and, if allowed, change resources and Helm releases.
- Community server
- Developer tools
At a glance
- Maintained by
- containers org (Red Hat-led open source project)
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Kubernetes runs containers across many servers, and understanding what is happening in a cluster takes experience. This MCP server lets an assistant list namespaces, pods and events, read logs, get resources and, when allowed, create, update or delete resources and install Helm charts.
For operations teams, it speeds up investigating incidents. An assistant can answer "why is this pod crashing" by reading events and logs in one go.
It is maintained by the containers organization, an open-source project led by Red Hat engineers, not by the Kubernetes project itself. It offers a read-only mode, which we use by default. Write access, including deleting pods and running commands inside them, belongs only in development clusters.
Paired with an error tracker and a code repository, it lets an assistant follow an incident from alert to cause in one conversation, which shortens the time an engineer spends collecting context.
Use cases
Best business use cases
Incident triage
Cluster overview
Config review
Helm installs
Team learning
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: reads cluster state and logs, and can create, update, scale and delete resources and Helm releases; read-only mode available.
-
configuration_viewShow the current kubeconfig as YAML.
-
namespaces_listList namespaces in the cluster.
-
events_listList cluster events for troubleshooting.
-
pods_listList pods in all namespaces.
-
pods_logGet a pod's logs.
-
pods_execRun a command in a pod.
-
pods_deleteDelete a pod.
-
resources_getGet any Kubernetes resource by apiVersion, kind and name.
-
resources_create_or_updateCreate or update a resource with Server-Side Apply.
-
helm_installInstall a Helm chart.
Workflows
Example workflows
Explain a crashing pod
-
1
Connect in read-only mode.
-
2
Ask why a pod is crashing.
-
3
The assistant reads events and logs.
-
4
It explains the likely cause.
-
5
An engineer applies the fix.
Namespace review
-
1
Ask for a summary of a namespace.
-
2
The assistant lists workloads and services.
-
3
It flags pods with restarts.
-
4
It notes missing resource limits.
-
5
The team plans fixes.
Prompts
Example prompts
“Why is the payments pod in the prod namespace restarting? Read its events and logs.”
“List all deployments without resource limits.”
“Summarize what is running in the staging namespace.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"kubernetes": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
]
}
}
}Claude Code: terminal
claude mcp add kubernetes -- npx -y kubernetes-mcp-server@latest- Local server: stdio; kubernetes-mcp-server; kubernetes-mcp-server.
- Needs: Kubeconfig (default ~/.kube/config, or KUBECONFIG env).
Security
Security considerations
-
Read-only mode
Use read-only mode for anything beyond development.
-
Limited kubeconfig
Use a service account with minimal roles.
-
Exec access
Running commands in pods is powerful. Disable it where possible.
-
Open-source project
Review the code and pin the version.
Related servers
Servers that pair well with it
Docker
A community MCP server that lets AI list, run, stop and remove Docker containers and manage images, networks and volumes.
AWS
The AWS API MCP server from AWS Labs lets AI run AWS CLI commands, suggest commands and plan changes, with read-only and consent modes.
Google Cloud
Google's gcloud MCP servers let AI run gcloud commands, read logs, metrics, alerts and traces, and work with Cloud Storage.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI copilots AI helpers built into your product or internal tools that draft, summarize and suggest while people decide.
- SaaS Product Development MVPs, subscription platforms, admin panels and multi-tenant products, planned to grow past the first launch.
- Automation and Integrations CRM, payment and API integrations, MCP connections and workflows that stop people copying data by hand.
- MVP development A first version with just enough features to put in front of real users and learn what to build next.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
Solutions
View all solutionsIndustries
View all industriesCase studies
View all case studiesGuides and articles
View all guides and articles- Where AI helps in development, and where it does not An honest map of the development tasks AI speeds up and the ones that still need experienced people.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- How to build a customer portal Plan and build a portal where customers see status, share documents and help themselves, safely.
AI models
View all ai models- Coding Models that write, review and explain code, and power coding assistants and developer tools.
- Mistral Medium 3.5 A newer open-weight Mistral model for agent and coding work, with image input, tool calling, structured outputs and a 256K window.
- Codestral 25.08 Mistral's low-latency coding model for code completion and generation, with fill-in-the-middle support, tool calling and a 128K window.
- GPT-6 Sol The middle model of the GPT-6 family, positioned for complex coding and agentic workflows at a mid price level.
- Qwen3-Coder Qwen's open-weight coding models under Apache 2.0, from the efficient Qwen3-Coder-Next to the large 480B model, with tool use and long context.
Glossary terms
View all glossary terms- API integration An API integration connects two or more systems through their APIs so data and actions flow between them automatically.
- Multi-tenant Multi-tenant describes software where one application and database serve many customers, called tenants, while keeping each customer's data separate.
- Claude Code Claude Code is Anthropic's agentic coding tool, which works in a developer's terminal, IDE, desktop app or browser to read code, run commands and make changes.
- AI copilot An AI copilot is an assistant built into a tool people already use, which suggests, drafts and explains while the person stays in control.
- Business process automation Business process automation uses software to run a multi-step business process, such as approvals or onboarding, from start to finish with less manual work.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
No. It is maintained by the containers organization, a Red Hat-led open-source project.
Yes, and we recommend it by default.
Yes, when write access is allowed.