Kubernetes MCP Server

Kubernetes is an open-source container orchestration platform for automating deployment, scaling, and management of containerized applications.

Tools

Last Updated

Apr 7, 2026

What is the Kubernetes MCP Server?

The Kubernetes MCP server gives AI agents structured, permission-aware access to Kubernetes through the Model Context Protocol. With 28 pre-built actions, agents can read, create, and update Kubernetes data on behalf of authorized users.

Willow ships the Kubernetes MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Kubernetes is being used by every AI agent in your stack.

Tools

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.

1 2 3

1–10 of 28 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your Kubernetes MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-kubernetes": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/kubernetes"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-kubernetes": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/kubernetes"
    }
  }
}

Claude Code

CLI

claude mcp add willow-kubernetes --transport http https://<org>.mcp-s.com/mcp/mcp/kubernetes

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/kubernetes",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Kubernetes

Willow adds the layer Kubernetes and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Kubernetes MCP Server FAQ

What is the Kubernetes MCP server?

The Kubernetes MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Kubernetes data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Kubernetes MCP server different from the official one?

The official Kubernetes MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Kubernetes MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Kubernetes MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Kubernetes, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Kubernetes actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Kubernetes MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Kubernetes MCP locally, you'll see it.

What does the Kubernetes MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Kubernetes MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.