kubeview-mcp 1.6.0 → 1.7.1

package/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.7.1] - 2026-03-07
+
+### Changed
+- **Refactor publishing scripts and add tests for release workflow**
+- **Enhance publish scripts and update README for clarity**
+- **Update publish:mcp script in package.json to remove login requirement for mcp-publisher**
+- **Refactor CLI run-command.js to simplify Kubernetes and Helm tool class handling**
+
+## [1.7.0] - 2026-02-17
+
+### Added
+- **feat(helm): add API-first backend support for Helm commands**
+- **feat(helm): add CLI fallback support for Helm v4 commands**
+
+### Changed
+- **Refactor CLI run-command.js to simplify Kubernetes and Helm tool class handling**
+
 ## [1.6.0] - 2026-02-04
 
 ### Changed

package/README.md

@@ -1,29 +1,23 @@
 # KubeView MCP – Kubernetes Model Context Protocol Server
 
+[![npm version](https://img.shields.io/npm/v/kubeview-mcp)](https://www.npmjs.com/package/kubeview-mcp)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Node.js Version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen)](https://nodejs.org/)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.8+-blue)](https://www.typescriptlang.org/)
 
-**KubeView** is a read-only Model Context Protocol (MCP) server that enables AI agents (like Cursor IDE, Claude Code CLI, Codex CLI, Gemini CLI, etc.) to inspect, diagnose, and debug Kubernetes clusters safely. It provides a comprehensive set of tools for Kubernetes, Helm, Argo Workflows, and Argo CD.
-Learn more about the benefits of code mode and implementation in [Evicting MCP tool calls from your Kubernetes cluster](https://dev.to/mikhae1/evicting-mcp-tool-calls-from-your-kubernetes-cluster-428k).
+**KubeView** is a read-only [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server that lets AI agents (Cursor, Claude Code, Codex CLI, Gemini CLI, etc.) safely inspect, diagnose, and debug Kubernetes clusters. It covers Kubernetes core, Helm, Argo Workflows, and Argo CD.
 
----
-
-## ✨ Features
-
-- **🧠 Code Mode**: Sandboxed TypeScript environment for complex reasoning and multi-step workflows.
-- **🛡️ Read-Only & Safe**: Designed for production safety with zero write access and sensitive data masking.
-- **☸️ Kubernetes Integration**: List/get resources, fetch metrics, stream logs and events, execute commands, and tools to diagnose network issues.
-- **📦 Helm Support**: Inspect releases, values, manifests, and history.
-- **🐙 Argo Ecosystem**: Manage Argo Workflows and Argo CD applications using direct Kubernetes API or CLI.
+> Read more: [Evicting MCP tool calls from your Kubernetes cluster](https://dev.to/mikhae1/evicting-mcp-tool-calls-from-your-kubernetes-cluster-428k)
 
 ---
 
-## MCP SDK Compatibility
+## ✨ Features
 
-- This project is pinned to `@modelcontextprotocol/sdk@^1.25.3`.
-- Legacy loose type imports (`Tools`, `Prompts`, `Resources`, `Roots`, `Sampling`) are disallowed.
-- This compatibility pass intentionally excludes Streamable HTTP transport migration and icon metadata rollout.
+- **🧠 Code Mode** – Sandboxed TypeScript runtime for complex reasoning and multi-step workflows.
+- **🛡️ Read-Only & Safe** – Zero write access; sensitive data masking for production clusters.
+- **☸️ Kubernetes** – List/get resources, fetch metrics, stream logs and events, exec into containers, diagnose network issues.
+- **📦 Helm (API-first)** – Inspect releases, values, manifests, and history via the Kubernetes API with CLI fallback.
+- **🐙 Argo Ecosystem** – Manage Argo Workflows and Argo CD via the Kubernetes API or CLI.
 
 ---
 
@@ -33,21 +27,21 @@ Learn more about the benefits of code mode and implementation in [Evicting MCP t
 
 - Node.js ≥ 18
 - Access to a Kubernetes cluster
-- Optionally, CLIs installed in current $PATH: `helm`, `argo`, `argocd`
+- Optional CLIs in `$PATH`: `helm` (fallback only), `argo`, `argocd`
 
 ### Installation
 
 ```bash
-# start the server
+# Run the server directly
 npx -y kubeview-mcp
 
-# install as a claude code mcp server
+# Add to Claude Code
 claude mcp add kubernetes -- npx kubeview-mcp
 ```
 
-### Configuration for MCP Clients
+### MCP Client Configuration
 
-Add to your `mcpServers` configuration (e.g., in Cursor or Claude Desktop):
+Add to your `mcpServers` config (Cursor, Claude Desktop, etc.):
 
 ```json
 {
@@ -62,104 +56,94 @@ Add to your `mcpServers` configuration (e.g., in Cursor or Claude Desktop):
 
 ### Environment Variables
 
-Configure the server using environment variables:
-
-| Variable | Description | Default |
-|----------|-------------|---------|
-| `KUBECONFIG` | Path to kubeconfig file | `~/.kube/config` |
-| `MCP_MODE` | Server mode: `all`, `code`, or `tools` | `all` |
-| `MCP_LOG_LEVEL` | Log level (`error`, `warn`, `info`, `debug`) | `info` |
-| `MCP_HIDE_SENSITIVE` | Enable global sensitive data masking | `false` |
+| Variable             | Description                                  | Default          |
+| -------------------- | -------------------------------------------- | ---------------- |
+| `KUBECONFIG`         | Path to kubeconfig file                      | `~/.kube/config` |
+| `MCP_MODE`           | Server mode: `all`, `code`, or `tools`       | `all`            |
+| `MCP_LOG_LEVEL`      | Log level: `error`, `warn`, `info`, `debug`  | `info`           |
+| `MCP_HIDE_SENSITIVE` | Mask sensitive data globally                 | `false`          |
 
 ---
 
-## 🛠️ Tools Overview
+## 🛠️ Tools
 
 ### Kubernetes
-- **`kube_list`**: List resources or get cluster diagnostics.
-- **`kube_get`**: Describe specific resources (supports all K8s types).
-- **`kube_metrics`**: Fetch CPU/memory metrics for nodes and pods.
-- **`kube_logs`**: Fetch or stream container logs.
-- **`kube_exec`**: Execute commands in containers (read-only recommended).
-- **`kube_port`**: Port-forward to pods/services.
-- **`kube_net`**: Run in-cluster network diagnostics.
+
+| Tool           | Description                                              |
+| -------------- | -------------------------------------------------------- |
+| `kube_list`    | List resources or get cluster diagnostics                |
+| `kube_get`     | Describe a specific resource (all K8s types supported)   |
+| `kube_metrics` | Fetch CPU/memory metrics for nodes and pods              |
+| `kube_logs`    | Fetch or stream container logs                           |
+| `kube_exec`    | Execute commands inside containers                       |
+| `kube_port`    | Port-forward to pods or services                         |
+| `kube_net`     | Run in-cluster network diagnostics                       |
 
 ### Helm
-- **`helm_list`**: List Helm releases.
-- **`helm_get`**: Fetch release values, manifests, and history.
+
+| Tool        | Description                                                       |
+| ----------- | ----------------------------------------------------------------- |
+| `helm_list` | List Helm releases (Kubernetes API first, CLI fallback)           |
+| `helm_get`  | Fetch release values, manifests, notes, hooks, status, history    |
+
+**Helm execution strategy:** Tools read Helm metadata directly from Kubernetes storage (Secrets / ConfigMaps) by default — no `helm` binary needed for standard read-only use. CLI fallback is used for non-JSON formatting or non-Kubernetes storage backends (e.g. SQL).
 
 ### Argo
-- **`argo_list` / `argo_get`**: Manage Argo Workflows.
-- **`argocd_app`**: Inspect Argo CD applications and resources.
+
+| Tool          | Description                              |
+| ------------- | ---------------------------------------- |
+| `argo_list`   | List Argo Workflows                      |
+| `argo_get`    | Inspect a specific Argo Workflow         |
+| `argocd_app`  | Inspect Argo CD applications             |
 
 ### Utilities
-- **`run_code`**: Execute sandboxed TypeScript code for complex tasks.
-- **`plan_step`**: Record step-by-step planning state for long, complex investigations.
 
-### Why `plan_step` really helps:
+| Tool        | Description                                                    |
+| ----------- | -------------------------------------------------------------- |
+| `run_code`  | Execute sandboxed TypeScript for complex tasks                 |
+| `plan_step` | Persist step-by-step planning state across long investigations |
 
-1. **Stable multi-step planning without bloating chat context.**
-   Instead of dumping a massive plan into the conversation, the agent can store step-by-step progress in `plan_step` and keep user-facing responses clean.
-2. **A consistent state machine for long tasks.**
-   Complex workflows usually need: plan -> execute step 1 -> verify -> step 2 -> backtrack -> branch -> finalize. `plan_step` gives the agent a structured way to follow that lifecycle without losing track.
-3. **Better tool routing.**
-   Good agents alternate between thinking and acting. `plan_step` encourages that rhythm: log intent, call real tools, capture outcome, decide next step.
+**Why `plan_step`?** It keeps the chat context clean by storing progress externally, gives agents a structured state machine (plan → execute → verify → branch), and encourages the think-then-act rhythm that produces better results on complex workflows.
 
 ---
 
 ## 🧠 Code Mode
 
-Inspired by [Code execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp), KubeView ships with a code-mode runtime that allows agents to explore the API, search tools, and execute complex workflows in a sandboxed environment.
-
-### What it provides
+Inspired by [Code execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp), KubeView ships a sandboxed code runtime for agents to explore the API and run complex workflows.
 
-- **MCP Bridge Layer**: Seamlessly connects to all registered MCP server tools.
-- **Dynamic TypeScript Definitions**: Automatically converts tool schemas into a strongly-typed `global.d.ts` resource, enabling agents to use valid TypeScript patterns and enjoy type safety without hallucinating parameters.
-- **Tool Search Utilities**: Runtime helpers like `tools.search()` and `tools.list()` allow agents to progressively discover capabilities without needing to load the entire schema context upfront.
-- **Sandboxed Execution**: A locked-down Node.js environment (via `vm`) with controlled access to the `console` and the `tools` global object, ensuring safe execution of agent-generated code.
+- **MCP Bridge** – All registered MCP tools are callable from within `run_code`.
+- **Dynamic TypeScript Definitions** – Tool schemas are auto-converted to a typed `global.d.ts`, preventing hallucinated parameters.
+- **Tool Discovery** – `tools.search()` and `tools.list()` let agents find capabilities at runtime without loading the full schema.
+- **Sandboxed Execution** – Locked-down Node.js `vm` environment with access only to `console` and the `tools` global.
 
-### Usage
-
-For complex tasks requiring logic, loops, or data processing, use **Code Mode**:
+Enable code-only mode:
 
 ```json
 "env": { "MCP_MODE": "code" }
 ```
 
-### 💡 Pro Tip: `code-mode` MCP Prompt
-
-The server includes a built-in MCP server prompt named **`code-mode`** that injects the full TypeScript API documentation, tool overview, and examples into the context.
+### Built-in `code-mode` Prompt
 
-**In Cursor IDE**:
-Simply type `/kubeview/code-mode` in the prompt (or select it from the `/` prompt menu). This gives the AI the exact context it needs to write correct `run_code` scripts immediately.
+The server includes a **`code-mode`** MCP prompt that injects full TypeScript API docs and examples into the agent context. In Cursor, type `/kubeview/code-mode` in the prompt bar to activate it.
 
 ---
 
 ## 💻 Local Development
 
-1. **Clone & Install**:
-   ```bash
-   git clone https://github.com/mikhae1/kubeview-mcp.git
-   cd kubeview-mcp
-   npm install
-   ```
-
-2. **Build & Run**:
-   ```bash
-   npm run build
-   npm start
-   ```
-
-3. **Test**:
-   ```bash
-   npm test
-   ```
+```bash
+# Clone and install
+git clone https://github.com/mikhae1/kubeview-mcp.git
+cd kubeview-mcp
+npm install
 
-### CLI Usage
+# Build and run
+npm run build
+npm start
 
-You can test tools directly via the CLI:
+# Test
+npm test
 
-```bash
+# Run a tool directly via CLI
 npm run command -- kube_list --namespace=default
 ```
 

package/SKILL.md

@@ -1,76 +1,81 @@
-# KubeView MCP Skills: Debugging Kubernetes Clusters
+---
+name: kubeview-debug
+description: Debug and diagnose Kubernetes clusters using KubeView MCP server tools. Use when investigating cluster issues (pod crashes, deployment failures, service connectivity problems, node issues, resource constraints), performing cluster health checks, or troubleshooting any Kubernetes workload. Trigger phrases include "cluster health", "pod won't start", "CrashLoopBackOff", "service unreachable", "deployment stuck", "node pressure", "OOMKilled", "ImagePullBackOff".
+---
+
+# Kubernetes Cluster Debugging
 
-This document contains reusable investigation playbooks ("skills") for debugging Kubernetes clusters using the KubeView MCP server.
+Reusable investigation playbooks for debugging Kubernetes clusters using KubeView MCP.
 
-## Assumptions & Constraints
+## Core Principles
 
-- **Read-Only by Design**: Avoid making state changes (edit, delete, scale) through these tools unless explicitly authorized.
-- **Documentation**: Use `search_tools` to find new capabilities.
-- **Prefer MCP Tools**: Use `kube_*` tools over shelling out to `kubectl`.
+- **Read-Only**: Avoid state changes unless explicitly authorized.
+- **Prefer MCP Tools**: Use `kube_*` tools over `kubectl` commands.
 - **Security First**: Treat output as potentially sensitive.
-- **Declarative over Imperative**: When suggesting fixes, provide YAML snippets rather than `kubectl patch/edit` commands.
+- **Declarative Fixes**: Provide YAML snippets rather than imperative `kubectl` commands.
 
-## Tool Quick Map
+## Tool Quick Reference
 
-- **Cluster + Workloads**: `kube_list`, `kube_get`, `kube_metrics`
+- **Cluster & Workloads**: `kube_list`, `kube_get`, `kube_metrics`
 - **Logs**: `kube_logs` (single pod), `kube_log` (multi-pod with filters + events)
 - **Network**: `kube_net`, `kube_exec`, `kube_port`
 - **Discovery**: `search_tools` (tools-mode), `run_code` (code-mode)
 
-In code-mode (`run_code`), these become `tools.kubernetes.*` (e.g., `tools.kubernetes.list`).
-
----
+In code-mode, tools become `tools.kubernetes.*` (e.g., `tools.kubernetes.list`).
 
 ## Debugging Decision Tree
 
 ```
 Issue reported
     │
-    ├─ Pod not running? ──────────► See: Debug a Pod that Won't Start
+    ├─ Pod not running? ──────────► Skill: Debug Pod Failures
     │
-    ├─ Service unreachable? ──────► See: Debug a Service With No Traffic
+    ├─ Service unreachable? ──────► Skill: Debug Service Connectivity
     │
-    ├─ Deployment stuck? ─────────► See: Debug a Deployment
+    ├─ Deployment stuck? ─────────► Skill: Debug Deployment Rollout
     │
-    ├─ Node issues? ──────────────► See: Node Debugging
+    ├─ Node issues? ──────────────► Skill: Node Debugging
     │
-    └─ Performance/Resources? ────► See: Resource Debugging
+    └─ Performance/Resources? ────► Skill: Resource Debugging
 ```
 
 ---
 
-## Skill: Cluster Triage (fast)
+## Skill: Cluster Triage
 
-**Intent**: Get a high-signal overview and decide where to drill down next.
+**When**: Get high-level cluster health overview, identify problem areas.
 
-**Procedure**:
+**Trigger**: "cluster health", "triage the cluster", "what's wrong"
 
-1. **Cluster overview (diagnostics)**
+**Steps**:
+
+1. **Cluster diagnostics**
    ```json
    { "tool": "kube_list", "args": {} }
    ```
 
-2. **Metrics + diagnostics**
+2. **Metrics + top consumers**
    ```json
    { "tool": "kube_metrics", "args": { "diagnostics": true, "includeSummary": true, "topN": 5 } }
    ```
 
-3. **Identify "Worst" Namespaces** (if not obvious)
-   - Look for high counts of `CrashLoopBackOff` or `Pending`.
-   - List pods in that namespace:
+3. **Drill into problem namespaces**
+   - Identify namespaces with high `CrashLoopBackOff` or `Pending` counts
    ```json
    { "tool": "kube_list", "args": { "namespace": "<ns>" } }
    ```
 
 ---
 
-## Skill: Debug a Pod that Won't Start / CrashLoop
+## Skill: Debug Pod Failures
+
+**When**: Pod is Pending, CrashLoopBackOff, ImagePullBackOff, or OOMKilled.
 
-**Intent**: Identify why a pod is Pending / CrashLoopBackOff / ImagePullBackOff / OOMKilled.
+**Trigger**: "pod won't start", "CrashLoopBackOff", "ImagePullBackOff", "OOMKilled"
 
-**Procedure**:
+**Steps**:
 
-1. **Describe the pod with events + diagnostics**
+1. **Describe pod with events**
    ```json
    {
      "tool": "kube_get",
@@ -84,7 +89,7 @@ Issue reported
    }
    ```
 
-2. **Pull logs (current & previous)**
+2. **Check logs (current & previous)**
    ```json
    {
      "tool": "kube_logs",
@@ -92,28 +97,25 @@ Issue reported
    }
    ```
 
-3. **Common Pod Issues Checklist**:
+3. **Common causes**:
    - **CrashLoopBackOff**:
-     - Exit Code 1: App error (check logs).
-     - Exit Code 137: OOMKilled (check memory limits vs usage).
-     - Exit Code 143: Graceful termination timeout or SIGTERM.
-   - **ImagePullBackOff**:
-     - Check image name/tag spelling.
-     - Check ImagePullSecrets (registry auth).
-   - **Pending**:
-     - Insufficient CPU/Memory (Cluster full?).
-     - Unsatisfiable Node Affinity/Selector.
-     - PVC binding failure.
+     - Exit 1: App error (check logs)
+     - Exit 137: OOMKilled (memory limit too low)
+     - Exit 143: SIGTERM timeout
+   - **ImagePullBackOff**: Check image name/tag, verify ImagePullSecrets
+   - **Pending**: Insufficient resources, node affinity issues, or PVC binding failure
 
 ---
 
-## Skill: Debug a Deployment / Rollout Not Progressing
+## Skill: Debug Deployment Rollout
+
+**When**: Deployment has 0 ready replicas or rollout not progressing.
 
-**Intent**: Explain why a deployment has missing/zero ready replicas.
+**Trigger**: "deployment stuck", "rollout not progressing", "0/1 ready"
 
-**Procedure**:
+**Steps**:
 
-1. **Check Deployment Status & Conditions**
+1. **Check deployment status**
    ```json
    {
      "tool": "kube_get",
@@ -126,7 +128,7 @@ Issue reported
    }
    ```
 
-2. **Inspect ReplicaSets** (Is a new RS failing to spin up?)
+2. **Inspect ReplicaSets** (Is new RS failing to create pods?)
    ```json
    {
      "tool": "kube_list",
@@ -134,7 +136,7 @@ Issue reported
    }
    ```
 
-3. **Aggregate Logs** (See if new pods are failing immediately)
+3. **Aggregate logs** (Are new pods failing immediately?)
    ```json
    {
      "tool": "kube_log",
@@ -148,29 +150,31 @@ Issue reported
    }
    ```
 
-**Common Issues**:
-- **Progressing Stuck**: New ReplicaSet can't create pods (quota? errors?).
-- **Available < Desired**: Pods running but failing Readiness Probe.
-- **Old ReplicaSets not cleaning up**: Deployment strategy issues.
+**Common issues**:
+- New ReplicaSet can't create pods (quota/errors?)
+- Pods running but failing readiness probe
+- Old ReplicaSets not cleaning up (strategy issue)
 
 ---
 
-## Skill: Debug a Service With No Traffic / No Endpoints
+## Skill: Debug Service Connectivity
 
-**Intent**: Determine if the issue is Selector, Pod Readiness, or Network Policy.
+**When**: Service has no traffic, endpoints missing, or unreachable.
 
-**Procedure**:
+**Trigger**: "service unreachable", "no endpoints", "can't reach service"
 
-1. **Verify Endpoints Exist**
+**Steps**:
+
+1. **Verify endpoints exist**
    ```json
    {
      "tool": "kube_get",
      "args": { "resourceType": "endpoints", "name": "<svc>", "namespace": "<ns>" }
    }
    ```
-   - *Empty?* Check Service Selector vs Pod Labels. Are pods Ready?
+   - Empty? Check Service selector vs Pod labels. Are pods Ready?
 
-2. **Test Connectivity from inside cluster**
+2. **Test connectivity from cluster**
    ```json
    {
      "tool": "kube_net",
@@ -188,53 +192,73 @@ Issue reported
 
 ## Skill: Node Debugging
 
-**Intent**: Identify if node-level issues (Pressure, Taints) are causing pod failures.
+**When**: Node-level issues causing pod failures.
+
+**Trigger**: "node not ready", "node pressure", "taints blocking pods"
 
-**Procedure**:
+**Steps**:
 
-1. **List Nodes & Status**
+1. **List nodes**
    ```json
    { "tool": "kube_list", "args": { "resourceType": "node" } }
    ```
 
-2. **Describe Specific Node**
+2. **Describe specific node**
    ```json
    { "tool": "kube_get", "args": { "resourceType": "node", "name": "<node>", "includeEvents": true } }
    ```
 
-**Conditions to Watch**:
-- **Ready**: Must be `True`.
-- **MemoryPressure / DiskPressure / PIDPressure**: If `True`, node is evicting/blocking pods.
-- **NetworkUnavailable**: CNI plugin failure?
+**Key conditions**:
+- **Ready**: Must be `True`
+- **MemoryPressure/DiskPressure/PIDPressure**: If `True`, node is evicting pods
+- **NetworkUnavailable**: CNI plugin failure
 
 ---
 
 ## Skill: Resource Debugging
 
-**Intent**: Detect resource bottlenecks (CPU throttling, OOM).
+**When**: Detecting resource bottlenecks (CPU throttling, OOM).
 
-**Procedure**:
+**Trigger**: "CPU throttling", "memory pressure", "high CPU/memory"
 
-1. **Top Pods/Nodes**
+**Steps**:
+
+1. **Top consumers**
    ```json
    { "tool": "kube_metrics", "args": { "topN": 10, "includeSummary": true } }
    ```
 
-2. **OOMKilled Investigation**
-   - Check `kube_get` pod status for `LastState: OOMKilled`.
-   - Solution: Increase Memory Limit or fix leak.
+2. **OOMKilled investigation**
+   - Check `kube_get` pod status for `LastState: OOMKilled`
+   - Solution: Increase memory limit or fix leak
+
+3. **CPU throttling**
+   - App slow but no errors? Check if usage near CPU limit
+   - Solution: Increase CPU limit or remove limit (keep request)
+
+---
+
+## Advanced: Code Mode Bulk Analysis
 
-3. **CPU Throttling**
-   - If app is slow but no errors: Check if usage is near CPU Limit.
-   - Solution: Increase CPU Limit (or remove limit and keep request).
+**When**: Complex queries requiring logic (e.g., "find all pods without resource limits").
+
+**Trigger**: "bulk analysis", "find pods without limits", "code mode"
+
+**Example**:
+```typescript
+const pods = await tools.kubernetes.list({ resourceType: 'pod' });
+const noLimits = pods.items.filter(p =>
+  p.spec.containers.some(c => !c.resources?.limits)
+);
+return { count: noLimits.length, names: noLimits.map(p => p.metadata.name) };
+```
 
 ---
 
-## Skill: Long Investigation Hygiene (using `plan_step`)
+## Multi-Step Investigation Hygiene
 
-**Intent**: Keep multi-step debugging stable and reviewable.
+For complex investigations spanning multiple steps, use `plan_step` to maintain clear progress tracking:
 
-**Template**:
 ```json
 {
   "tool": "plan_step",
@@ -246,18 +270,3 @@ Issue reported
   }
 }
 ```
-
----
-
-## Skill: One-shot Code Mode Triage (Advanced)
-
-**Intent**: Use `run_code` for complex logic (e.g., "Find all pods without resource limits").
-
-**Example**:
-```typescript
-const pods = await tools.kubernetes.list({ resourceType: 'pod' });
-const noLimits = pods.items.filter(p =>
-  p.spec.containers.some(c => !c.resources?.limits)
-);
-return { count: noLimits.length, names: noLimits.map(p => p.metadata.name) };
-```

package/dist/scripts/publish-mcp.d.ts

@@ -0,0 +1,3 @@
+#!/usr/bin/env tsx
+export {};
+//# sourceMappingURL=publish-mcp.d.ts.map

package/dist/scripts/publish-mcp.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"publish-mcp.d.ts","sourceRoot":"","sources":["../../scripts/publish-mcp.ts"],"names":[],"mappings":""}

package/dist/scripts/publish-mcp.js

@@ -0,0 +1,10 @@
+#!/usr/bin/env tsx
+import { publishMcp } from './release-publish';
+try {
+    publishMcp();
+}
+catch (error) {
+    console.error(error instanceof Error ? error.message : String(error));
+    process.exit(1);
+}
+//# sourceMappingURL=publish-mcp.js.map

package/dist/scripts/publish-mcp.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"publish-mcp.js","sourceRoot":"","sources":["../../scripts/publish-mcp.ts"],"names":[],"mappings":";AAEA,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAE/C,IAAI,CAAC;IACH,UAAU,EAAE,CAAC;AACf,CAAC;AAAC,OAAO,KAAK,EAAE,CAAC;IACf,OAAO,CAAC,KAAK,CAAC,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IACtE,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC"}

package/dist/scripts/release-publish.d.ts

@@ -0,0 +1,36 @@
+#!/usr/bin/env tsx
+type RunnerResult = {
+    status: number;
+    stdout: string;
+    stderr: string;
+    error?: NodeJS.ErrnoException;
+};
+type RunnerOptions = {
+    interactive?: boolean;
+    quiet?: boolean;
+    env?: NodeJS.ProcessEnv;
+};
+export type Runner = (command: string, args: string[], options?: RunnerOptions) => RunnerResult;
+type PublishStep = 'all' | 'commit' | 'tag' | 'npm' | 'git' | 'mcp';
+type PackageInfo = {
+    name: string;
+    version: string;
+};
+export declare function createRunner(options?: {
+    cwd?: string;
+    env?: NodeJS.ProcessEnv;
+    stdout?: Pick<NodeJS.WriteStream, 'write'>;
+    stderr?: Pick<NodeJS.WriteStream, 'write'>;
+}): Runner;
+export declare function publishMcp(options?: {
+    runner?: Runner;
+    cwd?: string;
+}): 'published' | 'skipped';
+export declare function runPublishWorkflow(options?: {
+    step?: PublishStep;
+    cwd?: string;
+    runner?: Runner;
+    packageInfo?: PackageInfo;
+}): void;
+export {};
+//# sourceMappingURL=release-publish.d.ts.map

package/dist/scripts/release-publish.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"release-publish.d.ts","sourceRoot":"","sources":["../../scripts/release-publish.ts"],"names":[],"mappings":";AAQA,KAAK,YAAY,GAAG;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,CAAC,EAAE,MAAM,CAAC,cAAc,CAAC;CAC/B,CAAC;AAEF,KAAK,aAAa,GAAG;IACnB,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,KAAK,CAAC,EAAE,OAAO,CAAC;IAChB,GAAG,CAAC,EAAE,MAAM,CAAC,UAAU,CAAC;CACzB,CAAC;AAEF,MAAM,MAAM,MAAM,GAAG,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,OAAO,CAAC,EAAE,aAAa,KAAK,YAAY,CAAC;AAEhG,KAAK,WAAW,GAAG,KAAK,GAAG,QAAQ,GAAG,KAAK,GAAG,KAAK,GAAG,KAAK,GAAG,KAAK,CAAC;AAEpE,KAAK,WAAW,GAAG;IACjB,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB,CAAC;AAWF,wBAAgB,YAAY,CAC1B,OAAO,GAAE;IACP,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,GAAG,CAAC,EAAE,MAAM,CAAC,UAAU,CAAC;IACxB,MAAM,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,WAAW,EAAE,OAAO,CAAC,CAAC;IAC3C,MAAM,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,WAAW,EAAE,OAAO,CAAC,CAAC;CACvC,GACL,MAAM,CA+BR;AA6FD,wBAAgB,UAAU,CACxB,OAAO,GAAE;IAAE,MAAM,CAAC,EAAE,MAAM,CAAC;IAAC,GAAG,CAAC,EAAE,MAAM,CAAA;CAAO,GAC9C,WAAW,GAAG,SAAS,CAkCzB;AAoED,wBAAgB,kBAAkB,CAChC,OAAO,GAAE;IACP,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,WAAW,CAAC,EAAE,WAAW,CAAC;CACtB,GACL,IAAI,CAyBN"}