feat(server): Add /live & /health endpoints

.github/workflows/helm-release.yml

@@ -0,0 +1,29 @@
+name: Release Charts
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  release:
+    # depending on default permission settings for your org (contents being read-only or read-write for workloads), you will have to add permissions
+    # see: https://docs.github.com/en/actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
+    permissions:
+      contents: write
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Configure Git
+        run: |
+          git config user.name "$GITHUB_ACTOR"
+          git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
+
+      - name: Run chart-releaser
+        uses: helm/chart-releaser-action@v1.7.0
+        env:
+          CR_TOKEN: "${{ secrets.GITHUB_TOKEN }}"

helm/nextcloud-mcp-server/README.md

@@ -157,6 +157,21 @@ ingress:
 | `autoscaling.maxReplicas` | Maximum replicas | `10` |
 | `autoscaling.targetCPUUtilizationPercentage` | Target CPU % | `80` |
 
+#### Health Probes
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `livenessProbe.httpGet.path` | Liveness probe endpoint | `/health/live` |
+| `livenessProbe.initialDelaySeconds` | Initial delay for liveness | `30` |
+| `livenessProbe.periodSeconds` | Check interval for liveness | `10` |
+| `readinessProbe.httpGet.path` | Readiness probe endpoint | `/health/ready` |
+| `readinessProbe.initialDelaySeconds` | Initial delay for readiness | `10` |
+| `readinessProbe.periodSeconds` | Check interval for readiness | `5` |
+
+The application exposes HTTP health check endpoints:
+- `/health/live` - Liveness probe (checks if application is running)
+- `/health/ready` - Readiness probe (checks if application is ready to serve traffic)
+
 #### Document Processing (Optional)
 
 | Parameter | Description | Default |
@@ -382,14 +397,41 @@ kubectl get pods -l app.kubernetes.io/name=nextcloud-mcp-server
 kubectl logs -l app.kubernetes.io/name=nextcloud-mcp-server --tail=100 -f
 ```
 
-### Test connectivity to Nextcloud
+### Check health endpoints
+
+The application exposes health check endpoints for monitoring:
 
 ```bash
 # Port forward to the service
 kubectl port-forward svc/nextcloud-mcp 8000:8000
 
-# In another terminal, test the connection
+# Check liveness (if app is running)
-curl http://localhost:8000/
+curl http://localhost:8000/health/live
+
+# Check readiness (if app is ready to serve traffic)
+curl http://localhost:8000/health/ready
+```
+
+**Example responses:**
+
+Liveness (always returns 200 if running):
+```json
+{
+  "status": "alive",
+  "mode": "basic"
+}
+```
+
+Readiness (returns 200 if ready, 503 if not ready):
+```json
+{
+  "status": "ready",
+  "checks": {
+    "nextcloud_configured": "ok",
+    "auth_mode": "basic",
+    "auth_configured": "ok"
+  }
+}
 ```
 
 ### Common Issues

helm/nextcloud-mcp-server/values.yaml

@@ -202,18 +202,24 @@ resources:
     memory: 128Mi
 
 # Liveness probe configuration
+# Checks if the application process is running
 livenessProbe:
-  tcpSocket:
+  httpGet:
+    path: /health/live
     port: http
+    scheme: HTTP
   initialDelaySeconds: 30
   periodSeconds: 10
   timeoutSeconds: 5
   failureThreshold: 3
 
 # Readiness probe configuration
+# Checks if the application is ready to serve traffic
 readinessProbe:
-  tcpSocket:
+  httpGet:
+    path: /health/ready
     port: http
+    scheme: HTTP
   initialDelaySeconds: 10
   periodSeconds: 5
   timeoutSeconds: 3

nextcloud_mcp_server/app.py

@@ -648,8 +648,71 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
                 await stack.enter_async_context(mcp.session_manager.run())
                 yield
 
+    # Health check endpoints for Kubernetes probes
+    def health_live(request):
+        """Liveness probe endpoint.
+
+        Returns 200 OK if the application process is running.
+        This is a simple check that doesn't verify external dependencies.
+        """
+        return JSONResponse(
+            {
+                "status": "alive",
+                "mode": "oauth" if oauth_enabled else "basic",
+            }
+        )
+
+    async def health_ready(request):
+        """Readiness probe endpoint.
+
+        Returns 200 OK if the application is ready to serve traffic.
+        Checks that required configuration is present.
+        """
+        checks = {}
+        is_ready = True
+
+        # Check Nextcloud host configuration
+        nextcloud_host = os.getenv("NEXTCLOUD_HOST")
+        if nextcloud_host:
+            checks["nextcloud_configured"] = "ok"
+        else:
+            checks["nextcloud_configured"] = "error: NEXTCLOUD_HOST not set"
+            is_ready = False
+
+        # Check authentication configuration
+        if oauth_enabled:
+            # OAuth mode - just verify we got this far (token_verifier initialized in lifespan)
+            checks["auth_mode"] = "oauth"
+            checks["auth_configured"] = "ok"
+        else:
+            # BasicAuth mode - verify credentials are set
+            username = os.getenv("NEXTCLOUD_USERNAME")
+            password = os.getenv("NEXTCLOUD_PASSWORD")
+            if username and password:
+                checks["auth_mode"] = "basic"
+                checks["auth_configured"] = "ok"
+            else:
+                checks["auth_mode"] = "basic"
+                checks["auth_configured"] = "error: credentials not set"
+                is_ready = False
+
+        status_code = 200 if is_ready else 503
+        return JSONResponse(
+            {
+                "status": "ready" if is_ready else "not_ready",
+                "checks": checks,
+            },
+            status_code=status_code,
+        )
+
     # Add Protected Resource Metadata (PRM) endpoint for OAuth mode
     routes = []
+
+    # Add health check routes (available in both OAuth and BasicAuth modes)
+    routes.append(Route("/health/live", health_live, methods=["GET"]))
+    routes.append(Route("/health/ready", health_ready, methods=["GET"]))
+    logger.info("Health check endpoints enabled: /health/live, /health/ready")
+
     if oauth_enabled:
 
         def oauth_protected_resource_metadata(request):