Kubernetes MCP in Claude Code

Quick answer: Install the Kubernetes MCP server with npx -y mcp-server-kubernetes, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on mcp-server-kubernetes as of April 15, 2026.

The Kubernetes MCP server wraps kubectl as a set of tools Claude Code can call. After setup, the model can list pods, read logs, describe resources, apply manifests, and restart deployments across any context in your kubeconfig. It is the fastest way to hand Claude a cluster surface without wiring up per-resource tools.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Kubernetes server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Kubernetes day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include list_pods, get_pod, describe_pod, get_logs, list_deployments, restart_deployment, apply_manifest, delete_resource, get_events. The server shells out to kubectl under the hood, so any flag supported by your kubectl version works. For clusters with custom auth (Azure AD, AWS IAM), make sure the helper binaries are on PATH.

Prerequisites

A working kubectl install with a populated kubeconfig. The user context that the server runs under needs RBAC permissions for whatever operations you expect Claude to perform. Node 20 or later.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y mcp-server-kubernetes

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": ["-y", "mcp-server-kubernetes"]
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List every pod in the namespace production and tell me which ones are not in Running state.
• Show me the last 200 log lines for pod api-server-abc123 in namespace production.
• Describe the deployment payments-service and tell me the current replica count and image tag.
• Restart the rollout for deployment web-frontend in namespace staging.
• Apply the manifest at ./k8s/cron-cleanup.yaml to the current context and confirm the resource was created.
• List every node in the cluster and tell me the CPU and memory capacity for each.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

No extra env vars beyond what kubectl already reads. The server picks up KUBECONFIG if set, otherwise it falls back to ~/.kube/config. For restricted access, create a dedicated service account with minimal RBAC and point a temporary kubeconfig at it. That keeps Claude from accidentally touching production when experimenting in dev.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Commands hang or fail with unable to connect. The current context points at an unreachable cluster. Check kubectl config current-context and kubectl cluster-info. If the cluster is behind a VPN, connect first before launching Claude Code.

Actions fail with forbidden. The kubeconfig user lacks the RBAC permission the operation needs. Run kubectl auth can-i to confirm, and have a cluster admin grant the role you need.

Logs tool returns truncated output. Ask Claude to pass a tail-lines argument and filter by time window rather than pulling the full log. For multi-pod logs, collect per pod and merge in the prompt.

Apply tool modifies a resource but the cluster state does not change. Server-side apply can silently lose fields if another controller owns them. Ask Claude to show the resulting diff after apply, and if in doubt, use a strategic merge patch instead.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Kubernetes server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.