Kubeview

KubeView MCP

Read-only Model Context Protocol server for Kubernetes diagnostics. Instead of exposing dozens of tools, it gives the agent a sandboxed TypeScript runtime: a single run_code call can query Kubernetes, Helm, Argo Workflows, and Argo CD, correlate the results, and return only the answer. Intermediate payloads never pass through the model's context window. Based on the code execution with MCP pattern.

Background: Evicting MCP tool calls from your Kubernetes cluster

How it works

v2 publishes exactly two public tools: run_code and an approval-gated kube_pod_exec. Everything else is discovered inside the sandbox via tools.list(), tools.search(), and tools.help(), following the MCP progressive discovery and programmatic calling guidance.

run_code executes bounded TypeScript with top-level await. One call can list workloads, correlate events, fetch logs, and diff Helm state without shipping intermediate payloads back through the model:

const pods = await tools.kubernetes.list({ namespace: 'payments' });

const unhealthy = pods.items.filter((p) => p.status?.phase !== 'Running');

return Promise.all( unhealthy.map(async (pod) => ({ pod: pod.metadata?.name, logs: await tools.kubernetes.logs({ namespace: 'payments', podName: pod.metadata?.name, tailLines: 100, }), })), );

• Sensitive isolation — kube_pod_exec is unreachable from sandboxed code. Top-level exec requires MCP elicitation, is bound to the argument digest, expires after 10 minutes, and fails closed. kube_port_forward is never a top-level tool and is denied inside code mode by default. tools.disabled() reports which policy blocked a capability and whether that denial is configurable.
• API-driven discovery — Argo Workflows and Argo CD are detected from the Kubernetes API, scoped to the active kube context, cached for 60 s. An unavailable optional API never blocks startup.
• Native reads — resources, metrics, logs, events, and network probes go through the Kubernetes API. Helm releases are parsed from cluster Secrets or ConfigMaps; a local helm binary is a fallback, not a prerequisite.

Quick start

Prerequisites: Node.js ≥ 22 and access to a cluster (KUBECONFIG or in-cluster service account).

npx -y kubeview-mcp

Claude Code

claude mcp add kubernetes -- npx kubeview-mcp

{

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

In Cursor, /kubeview/code-mode injects the typed API into context.

Configuration

Cluster

Mode and capabilities

HTTP transport

mkdir -p /tmp/kubeview-mcp-approvals

MCP_APPROVAL_STATE_SECRET='replace-with-at-least-32-random-bytes' \ MCP_APPROVAL_REPLAY_DIR=/tmp/kubeview-mcp-approvals \ MCP_TRANSPORT=http MCP_HTTP_HOST=127.0.0.1 MCP_HTTP_PORT=3000 npx -y kubeview-mcp

Endpoint: http://127.0.0.1:3000/mcp. HTTP follows the MCP 2026-07-28 stateless core: a fresh server per request, no initialize, no Mcp-Session-Id. Each request carries protocol version, client identity, and capabilities in _meta; modern requests add Mcp-Method/Mcp-Name for gateway routing. 2025-era clients use the SDK's stateless fallback on the same endpoint. State that must survive across calls has to be passed as tool arguments or handles.

HTTP mode refuses to start without both approval variables. Multi-replica deployments need the same secret and a shared writable replay directory; the /tmp example is for a single process only. The published MCP registry entry still targets stdio.

Tool surfaces

Domain tools use an operation discriminator:

• helm — list \| get \| debug
• argo — list \| get \| logs \| cron_list (when Workflow or CronWorkflow is discoverable)
• argocd — list \| get \| resources \| logs \| history \| status (when Application is discoverable, or with ARGOCD_SERVER + ARGOCD_AUTH_TOKEN)

Discovery is cached per kube context for 60 s. Missing optional APIs are omitted, not fatal. argo and argocd are registered when the API exists in the default context or in any exact context name listed in MCP_KUBE_CONTEXTS.

Multiple clusters

Every cluster tool accepts an optional context argument (a kubeconfig context name or an MCP_KUBE_CONTEXTS alias); kube_contexts lists the contexts you can target. Without it, calls behave as before: MCP_KUBE_CONTEXT, then the kubeconfig current-context. Context is per call rather than per session, which keeps HTTP mode stateless and lets one script query several clusters concurrently.

MCP_KUBE_CONTEXTS is a comma-separated list. Plain entries are context names with optional * wildcards; alias=context entries map a short name to a real context. Once set, only matching contexts, alias targets, and MCP_KUBE_CONTEXT are reachable, including for Helm/Argo/Argo CD CLI fallbacks, which receive --kube-context/--context for the resolved context. Add * to keep every context while defining aliases.

MCP_KUBE_CONTEXT=dev \

MCP_KUBE_CONTEXTS='dev,staging-*,prod=arn:aws:eks:eu-west-1:123456789012:cluster/prod' \ npx -y kubeview-mcp

In run_code, set a default for the whole script with the context argument, or scope it with tools.withContext(); a per-call context always wins:

const staging = tools.withContext('staging-eu');

const [stagingApi, prodApi] = await Promise.all([ staging.kubernetes.diagnose({ resourceType: 'deployment', name: 'api', namespace: 'shop' }), tools.kubernetes.diagnose({ resourceType: 'deployment', name: 'api', namespace: 'shop', context: 'prod' }), ]); return { staging: stagingApi.summary, prod: prodApi.summary };

kube_pod_exec resolves the context before asking for approval; the approval prompt names it, and the approval is bound to it.

Code mode

Code mode is the default (MCP_MODE=code). The agent writes short TypeScript against a typed tools global instead of calling dozens of MCP tools.

Inside run_code:

• Typed tools namespaces for Kubernetes, Helm, and any detected Argo capabilities, generated from live schemas so parameters cannot be hallucinated.
• Progressive discovery: tools.list(), tools.search(), tools.help(), and tools.disabled() (the last reports *why* a capability was blocked).
• Multi-cluster access: tools.kubernetes.contexts(), tools.withContext(name), and per-call context arguments (see Multiple clusters).
• A locked-down runtime with only console and tools in scope — no filesystem, no network, no process.

| Everything else | Available | Only when MCP_MODE=tools