feat: add MCP healthcheck probes and new templates (grafana, home-assistant, node-red)

- Add healthCheck spec to templates and servers (tool, arguments, interval, timeout, failureThreshold)
- Add healthStatus, lastHealthCheck, events fields to instances
- Create grafana, home-assistant, node-red templates with healthcheck probes
- Add healthcheck probes to existing templates (github, slack, postgres, jira)
- Show HEALTH column in `get instances` and Events section in `describe instance`
- Display healthCheck details in `describe server` and `describe template`
- Schema + storage + display only; actual probe runner is future work

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/cli/src/commands/apply.ts

@@ -4,6 +4,14 @@ import yaml from 'js-yaml';
 import { z } from 'zod';
 import type { ApiClient } from '../api-client.js';
 
+const HealthCheckSchema = z.object({
+  tool: z.string().min(1),
+  arguments: z.record(z.unknown()).default({}),
+  intervalSeconds: z.number().int().min(5).max(3600).default(60),
+  timeoutSeconds: z.number().int().min(1).max(120).default(10),
+  failureThreshold: z.number().int().min(1).max(20).default(3),
+});
+
 const ServerEnvEntrySchema = z.object({
   name: z.string().min(1),
   value: z.string().optional(),
@@ -24,6 +32,7 @@ const ServerSpecSchema = z.object({
   containerPort: z.number().int().min(1).max(65535).optional(),
   replicas: z.number().int().min(0).max(10).default(1),
   env: z.array(ServerEnvEntrySchema).default([]),
+  healthCheck: HealthCheckSchema.optional(),
 });
 
 const SecretSpecSchema = z.object({
@@ -51,6 +60,7 @@ const TemplateSpecSchema = z.object({
   containerPort: z.number().int().min(1).max(65535).optional(),
   replicas: z.number().int().min(0).max(10).default(1),
   env: z.array(TemplateEnvEntrySchema).default([]),
+  healthCheck: HealthCheckSchema.optional(),
 });
 
 const ProjectSpecSchema = z.object({

src/cli/src/commands/describe.ts

@@ -50,6 +50,19 @@ function formatServerDetail(server: Record<string, unknown>): string {
     }
   }
 
+  const hc = server.healthCheck as { tool: string; arguments?: Record<string, unknown>; intervalSeconds?: number; timeoutSeconds?: number; failureThreshold?: number } | null;
+  if (hc) {
+    lines.push('');
+    lines.push('Health Check:');
+    lines.push(`  ${pad('Tool:', 22)}${hc.tool}`);
+    if (hc.arguments && Object.keys(hc.arguments).length > 0) {
+      lines.push(`  ${pad('Arguments:', 22)}${JSON.stringify(hc.arguments)}`);
+    }
+    lines.push(`  ${pad('Interval:', 22)}${hc.intervalSeconds ?? 60}s`);
+    lines.push(`  ${pad('Timeout:', 22)}${hc.timeoutSeconds ?? 10}s`);
+    lines.push(`  ${pad('Failure Threshold:', 22)}${hc.failureThreshold ?? 3}`);
+  }
+
   lines.push('');
   lines.push('Metadata:');
   lines.push(`  ${pad('ID:', 12)}${server.id}`);
@@ -67,6 +80,16 @@ function formatInstanceDetail(instance: Record<string, unknown>, inspect?: Recor
   lines.push(`${pad('Container ID:')}${instance.containerId ?? '-'}`);
   lines.push(`${pad('Port:')}${instance.port ?? '-'}`);
 
+  // Health section
+  const healthStatus = instance.healthStatus as string | null;
+  const lastHealthCheck = instance.lastHealthCheck as string | null;
+  if (healthStatus || lastHealthCheck) {
+    lines.push('');
+    lines.push('Health:');
+    lines.push(`  ${pad('Status:', 16)}${healthStatus ?? 'unknown'}`);
+    if (lastHealthCheck) lines.push(`  ${pad('Last Check:', 16)}${lastHealthCheck}`);
+  }
+
   const metadata = instance.metadata as Record<string, unknown> | undefined;
   if (metadata && Object.keys(metadata).length > 0) {
     lines.push('');
@@ -88,6 +111,19 @@ function formatInstanceDetail(instance: Record<string, unknown>, inspect?: Recor
     }
   }
 
+  // Events section (k8s-style)
+  const events = instance.events as Array<{ timestamp: string; type: string; message: string }> | undefined;
+  if (events && events.length > 0) {
+    lines.push('');
+    lines.push('Events:');
+    const tsW = 26;
+    const typeW = 10;
+    lines.push(`  ${'TIMESTAMP'.padEnd(tsW)}${'TYPE'.padEnd(typeW)}MESSAGE`);
+    for (const ev of events) {
+      lines.push(`  ${(ev.timestamp ?? '').padEnd(tsW)}${(ev.type ?? '').padEnd(typeW)}${ev.message ?? ''}`);
+    }
+  }
+
   lines.push('');
   lines.push(`  ${pad('ID:', 12)}${instance.id}`);
   if (instance.createdAt) lines.push(`  ${pad('Created:', 12)}${instance.createdAt}`);
@@ -177,6 +213,19 @@ function formatTemplateDetail(template: Record<string, unknown>): string {
     }
   }
 
+  const hc = template.healthCheck as { tool: string; arguments?: Record<string, unknown>; intervalSeconds?: number; timeoutSeconds?: number; failureThreshold?: number } | null;
+  if (hc) {
+    lines.push('');
+    lines.push('Health Check:');
+    lines.push(`  ${pad('Tool:', 22)}${hc.tool}`);
+    if (hc.arguments && Object.keys(hc.arguments).length > 0) {
+      lines.push(`  ${pad('Arguments:', 22)}${JSON.stringify(hc.arguments)}`);
+    }
+    lines.push(`  ${pad('Interval:', 22)}${hc.intervalSeconds ?? 60}s`);
+    lines.push(`  ${pad('Timeout:', 22)}${hc.timeoutSeconds ?? 10}s`);
+    lines.push(`  ${pad('Failure Threshold:', 22)}${hc.failureThreshold ?? 3}`);
+  }
+
   lines.push('');
   lines.push('Usage:');
   lines.push(`  mcpctl create server my-${template.name} --from-template=${template.name}`);

src/cli/src/commands/get.ts

@@ -45,6 +45,7 @@ interface InstanceRow {
   status: string;
   containerId: string | null;
   port: number | null;
+  healthStatus: string | null;
 }
 
 const serverColumns: Column<ServerRow>[] = [
@@ -78,6 +79,7 @@ const templateColumns: Column<TemplateRow>[] = [
 
 const instanceColumns: Column<InstanceRow>[] = [
   { header: 'STATUS', key: 'status', width: 10 },
+  { header: 'HEALTH', key: (r) => r.healthStatus ?? '-', width: 10 },
   { header: 'SERVER ID', key: 'serverId' },
   { header: 'PORT', key: (r) => r.port != null ? String(r.port) : '-', width: 6 },
   { header: 'CONTAINER', key: (r) => r.containerId ? r.containerId.slice(0, 12) : '-', width: 14 },