Bootstrap initial repo state

helm/mcp-telemetry-bridge/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+name: mcp-telemetry-bridge
+description: MCP Telemetry Bridge for TeleMcp
+type: application
+version: 0.1.0
+appVersion: "0.1.0"

helm/mcp-telemetry-bridge/templates/deployment.yaml

@@ -0,0 +1,35 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: mcp-telemetry-bridge
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels: { app: mcp-telemetry-bridge }
+  template:
+    metadata:
+      labels: { app: mcp-telemetry-bridge }
+    spec:
+      serviceAccountName: {{ .Values.serviceAccount.name }}
+      containers:
+        - name: bridge
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: 8000
+          env:
+          {{- range .Values.env }}
+            - name: {{ .name }}
+              value: "{{ .value }}"
+          {{- end }}
+          readinessProbe:
+            httpGet: { path: /healthz, port: http }
+            initialDelaySeconds: 3
+            periodSeconds: 5
+          livenessProbe:
+            httpGet: { path: /healthz, port: http }
+            initialDelaySeconds: 10
+            periodSeconds: 10
+          resources:
+{{ toYaml .Values.resources | indent 12 }}

helm/mcp-telemetry-bridge/templates/networkpolicy.yaml

@@ -0,0 +1,21 @@
+{{- if .Values.networkPolicy.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: mcp-telemetry-bridge-deny-all
+spec:
+  podSelector:
+    matchLabels:
+      app: mcp-telemetry-bridge
+  policyTypes: ["Ingress","Egress"]
+  ingress:
+  - {}  # allow same-namespace by default; tighten as needed
+  egress:
+  - to:
+    - namespaceSelector: {}
+    ports:
+    - protocol: TCP
+      port: 9090  # Prometheus
+    - protocol: TCP
+      port: 3100  # Loki
+{{- end }}

helm/mcp-telemetry-bridge/templates/rbac.yaml

@@ -0,0 +1,26 @@
+{{- if .Values.rbac.create }}
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: mcp-telemetry-readonly
+rules:
+  - apiGroups: [""]
+    resources: ["pods","pods/log","nodes","events","namespaces","services","endpoints"]
+    verbs: ["get","list","watch"]
+  - apiGroups: ["apps"]
+    resources: ["deployments","daemonsets","statefulsets","replicasets"]
+    verbs: ["get","list","watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: mcp-telemetry-readonly-binding
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: mcp-telemetry-readonly
+subjects:
+  - kind: ServiceAccount
+    name: {{ .Values.serviceAccount.name }}
+    namespace: {{ .Release.Namespace }}
+{{- end }}

helm/mcp-telemetry-bridge/templates/service.yaml

@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: mcp-telemetry-bridge
+spec:
+  selector: { app: mcp-telemetry-bridge }
+  ports:
+    - name: http
+      port: {{ .Values.service.port }}
+      targetPort: 8000
+  type: {{ .Values.service.type }}

helm/mcp-telemetry-bridge/templates/serviceaccount.yaml

@@ -0,0 +1,6 @@
+{{- if .Values.serviceAccount.create }}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ .Values.serviceAccount.name }}
+{{- end }}

helm/mcp-telemetry-bridge/values.yaml

@@ -0,0 +1,37 @@
+image:
+  repository: ghcr.io/example/telemcp-bridge
+  tag: "0.1.0"
+  pullPolicy: IfNotPresent
+
+replicaCount: 1
+
+service:
+  type: ClusterIP
+  port: 80
+
+env:
+  - name: PROM_URL
+    value: "http://monitoring-kube-prometheus-prometheus.monitoring:9090"
+  - name: LOKI_URL
+    value: "http://loki.logging:3100"
+  - name: K8S_API
+    value: "https://kubernetes.default.svc"
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+rbac:
+  create: true
+
+serviceAccount:
+  create: true
+  name: mcp-telemetry
+
+networkPolicy:
+  enabled: true
+  allowFromNamespaces: []   # add namespace selectors if needed

helm/values/kube-prometheus-stack.values.yaml

@@ -0,0 +1,25 @@
+kube-state-metrics:
+  enabled: true
+
+prometheus:
+  prometheusSpec:
+    retention: 5d
+    scrapeInterval: 15s
+    enableAdminAPI: false
+    resources:
+      requests:
+        cpu: 100m
+        memory: 512Mi
+
+alertmanager:
+  alertmanagerSpec:
+    replicas: 1
+
+defaultRules:
+  create: true
+  rules:
+    kubeApiserverError: true
+    kubeNodeNotReady: true
+    kubePodCrashLooping: true
+    kubeJobFailed: true
+    etcdHighNumberOfFailedGRPCRequests: true

helm/values/loki.values.yaml

@@ -0,0 +1,15 @@
+loki:
+  auth_enabled: false
+  commonConfig:
+    replication_factor: 1
+  storage:
+    type: filesystem
+  schemaConfig:
+    configs:
+      - from: "2024-01-01"
+        store: boltdb-shipper
+        object_store: filesystem
+        schema: v13
+        index:
+          prefix: index_
+          period: 24h

helm/values/otel-collector.values.yaml

@@ -0,0 +1,22 @@
+mode: deployment
+config:
+  receivers:
+    otlp:
+      protocols: { http: {}, grpc: {} }
+  processors:
+    batch: {}
+  exporters:
+    prometheusremotewrite:
+      endpoint: "http://monitoring-kube-prometheus-prometheus.monitoring:9090/api/v1/write"
+    loki:
+      endpoint: "http://loki.logging:3100/loki/api/v1/push"
+  service:
+    pipelines:
+      metrics:
+        receivers: [otlp]
+        processors: [batch]
+        exporters: [prometheusremotewrite]
+      logs:
+        receivers: [otlp]
+        processors: [batch]
+        exporters: [loki]