Merge pull request #274 from cbcoutinho/feature/observability-monitoring

feature/observability monitoring
This commit is contained in:
Chris Coutinho
2025-11-09 09:29:25 +01:00
committed by GitHub
8 changed files with 921 additions and 3 deletions
@@ -0,0 +1,90 @@
# Grafana Dashboards
This directory contains example Grafana dashboards for monitoring the Nextcloud MCP Server.
## Dashboards
### nextcloud-mcp-server.json
Comprehensive dashboard with the following panels:
- **Request Rate**: HTTP requests per second by method and endpoint
- **Error Rate**: Percentage of 5xx errors
- **Request Latency**: P50 and P95 latency by endpoint
- **Top MCP Tools**: Most frequently called tools
- **Nextcloud API Latency**: API call latency by app (notes, calendar, etc.)
- **Vector Sync Queue**: Queue size for background document processing
## Importing to Grafana
### Manual Import
1. Open Grafana UI
2. Navigate to Dashboards → Import
3. Upload `nextcloud-mcp-server.json`
4. Select your Prometheus data source
5. Click "Import"
### Automated Import (Kubernetes)
If using the Grafana Operator or kube-prometheus-stack, you can create a ConfigMap:
```bash
kubectl create configmap nextcloud-mcp-dashboards \
--from-file=nextcloud-mcp-server.json \
-n monitoring
# Add label for Grafana sidecar to discover
kubectl label configmap nextcloud-mcp-dashboards \
grafana_dashboard=1 \
-n monitoring
```
Or add to your Helm values:
```yaml
# values.yaml for kube-prometheus-stack
grafana:
dashboardProviders:
dashboardproviders.yaml:
apiVersion: 1
providers:
- name: 'nextcloud-mcp'
orgId: 1
folder: 'Nextcloud MCP'
type: file
disableDeletion: false
editable: true
options:
path: /var/lib/grafana/dashboards/nextcloud-mcp
dashboardsConfigMaps:
nextcloud-mcp: nextcloud-mcp-dashboards
```
## Dashboard Variables
The dashboard includes two variables:
- **Data Source**: Select your Prometheus data source
- **Namespace**: Filter metrics by Kubernetes namespace
## Customization
You can customize the dashboard by:
1. Adjusting refresh rate (default: 30s)
2. Modifying time range (default: last 6 hours)
3. Adding new panels for specific metrics
4. Adjusting thresholds in existing panels
## Metrics Reference
All metrics are documented in `/docs/observability.md`. Key metric prefixes:
- `mcp_http_*` - HTTP server metrics
- `mcp_tool_*` - MCP tool invocation metrics
- `mcp_nextcloud_api_*` - Nextcloud API call metrics
- `mcp_oauth_*` - OAuth token validation metrics
- `mcp_vector_sync_*` - Vector database sync metrics
- `mcp_db_*` - Database operation metrics
@@ -0,0 +1,630 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"legend": {
"calcs": ["mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(rate(mcp_http_requests_total{namespace=\"$namespace\"}[5m])) by (method, endpoint)",
"legendFormat": "{{method}} {{endpoint}}",
"refId": "A"
}
],
"title": "Request Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "line"
}
},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 1
},
{
"color": "red",
"value": 5
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"id": 2,
"options": {
"legend": {
"calcs": ["mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(rate(mcp_http_requests_total{status_code=~\"5..\", namespace=\"$namespace\"}[5m])) / sum(rate(mcp_http_requests_total{namespace=\"$namespace\"}[5m])) * 100",
"legendFormat": "Error Rate",
"refId": "A"
}
],
"title": "Error Rate (%)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 3,
"options": {
"legend": {
"calcs": ["mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.95, sum(rate(mcp_http_request_duration_seconds_bucket{namespace=\"$namespace\"}[5m])) by (le, endpoint))",
"legendFormat": "{{endpoint}} (p95)",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.50, sum(rate(mcp_http_request_duration_seconds_bucket{namespace=\"$namespace\"}[5m])) by (le, endpoint))",
"legendFormat": "{{endpoint}} (p50)",
"refId": "B"
}
],
"title": "Request Latency (P50/P95)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"id": 4,
"options": {
"legend": {
"calcs": ["mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk(10, sum(rate(mcp_tool_calls_total{namespace=\"$namespace\"}[5m])) by (tool_name))",
"legendFormat": "{{tool_name}}",
"refId": "A"
}
],
"title": "Top MCP Tools by Volume",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"id": 5,
"options": {
"legend": {
"calcs": ["mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.95, sum(rate(mcp_nextcloud_api_duration_seconds_bucket{namespace=\"$namespace\"}[5m])) by (le, app))",
"legendFormat": "{{app}} (p95)",
"refId": "A"
}
],
"title": "Nextcloud API Latency by App",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"id": 6,
"options": {
"legend": {
"calcs": ["mean", "lastNotNull"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "mcp_vector_sync_queue_size{namespace=\"$namespace\"}",
"legendFormat": "Queue Size",
"refId": "A"
}
],
"title": "Vector Sync Queue Size",
"type": "timeseries"
}
],
"refresh": "30s",
"schemaVersion": 38,
"style": "dark",
"tags": ["nextcloud", "mcp", "observability"],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "Prometheus",
"value": "Prometheus"
},
"hide": 0,
"includeAll": false,
"label": "Data Source",
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"current": {
"selected": false,
"text": "default",
"value": "default"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(mcp_http_requests_total, namespace)",
"hide": 0,
"includeAll": false,
"label": "Namespace",
"multi": false,
"name": "namespace",
"options": [],
"query": {
"query": "label_values(mcp_http_requests_total, namespace)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
}
]
},
"time": {
"from": "now-6h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Nextcloud MCP Server",
"uid": "nextcloud-mcp-server",
"version": 1,
"weekStart": ""
}
@@ -56,6 +56,11 @@ spec:
- name: http
containerPort: {{ include "nextcloud-mcp-server.port" . }}
protocol: TCP
{{- if .Values.observability.metrics.enabled }}
- name: metrics
containerPort: {{ .Values.observability.metrics.port }}
protocol: TCP
{{- end }}
env:
# Nextcloud connection
- name: NEXTCLOUD_HOST
@@ -200,6 +205,27 @@ spec:
value: {{ .Values.openai.baseUrl | quote }}
{{- end }}
{{- end }}
# Observability
- name: METRICS_ENABLED
value: {{ .Values.observability.metrics.enabled | quote }}
- name: METRICS_PORT
value: {{ .Values.observability.metrics.port | quote }}
{{- if .Values.observability.tracing.enabled }}
- name: OTEL_ENABLED
value: "true"
- name: OTEL_EXPORTER_OTLP_ENDPOINT
value: {{ .Values.observability.tracing.endpoint | quote }}
- name: OTEL_SERVICE_NAME
value: {{ .Values.observability.tracing.serviceName | quote }}
- name: OTEL_TRACES_SAMPLER_ARG
value: {{ .Values.observability.tracing.samplingRate | quote }}
{{- end }}
- name: LOG_FORMAT
value: {{ .Values.observability.logging.format | quote }}
- name: LOG_LEVEL
value: {{ .Values.observability.logging.level | quote }}
- name: LOG_INCLUDE_TRACE_CONTEXT
value: {{ .Values.observability.logging.includeTraceContext | quote }}
{{- with .Values.extraEnv }}
{{- toYaml . | nindent 12 }}
{{- end }}
@@ -0,0 +1,92 @@
{{- if and .Values.observability.metrics.enabled .Values.prometheusRule.enabled }}
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: {{ include "nextcloud-mcp-server.fullname" . }}
namespace: {{ .Release.Namespace }}
labels:
{{- include "nextcloud-mcp-server.labels" . | nindent 4 }}
{{- with .Values.prometheusRule.labels }}
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
groups:
- name: nextcloud-mcp-server.critical
interval: 30s
rules:
- alert: NextcloudMCPServerDown
expr: up{job="{{ include "nextcloud-mcp-server.fullname" . }}"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Nextcloud MCP Server is down"
description: "{{ `{{` }} $labels.pod {{ `}}` }} has been down for more than 5 minutes."
- alert: NextcloudMCPHighErrorRate
expr: |
sum(rate(mcp_http_requests_total{status_code=~"5..", job="{{ include "nextcloud-mcp-server.fullname" . }}"}[5m]))
/ sum(rate(mcp_http_requests_total{job="{{ include "nextcloud-mcp-server.fullname" . }}"}[5m])) > 0.05
for: 5m
labels:
severity: critical
annotations:
summary: "High error rate on Nextcloud MCP Server"
description: "Error rate is {{ `{{` }} printf \"%.2f%%\" (mul $value 100) {{ `}}` }} (threshold: 5%)"
- alert: NextcloudMCPHighLatency
expr: |
histogram_quantile(0.95,
sum(rate(mcp_http_request_duration_seconds_bucket{job="{{ include "nextcloud-mcp-server.fullname" . }}"}[5m])) by (le, endpoint)
) > 1
for: 5m
labels:
severity: critical
annotations:
summary: "High latency on Nextcloud MCP Server"
description: "P95 latency is {{ `{{` }} printf \"%.2fs\" $value {{ `}}` }} on {{ `{{` }} $labels.endpoint {{ `}}` }} (threshold: 1s)"
- alert: NextcloudMCPDependencyDown
expr: mcp_dependency_health{job="{{ include "nextcloud-mcp-server.fullname" . }}"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: "Nextcloud MCP dependency is down"
description: "Dependency {{ `{{` }} $labels.dependency {{ `}}` }} has been down for more than 2 minutes."
- name: nextcloud-mcp-server.warning
interval: 30s
rules:
- alert: NextcloudMCPTokenValidationErrors
expr: |
sum(rate(mcp_oauth_token_validations_total{result="error", job="{{ include "nextcloud-mcp-server.fullname" . }}"}[10m]))
/ sum(rate(mcp_oauth_token_validations_total{job="{{ include "nextcloud-mcp-server.fullname" . }}"}[10m])) > 0.01
for: 10m
labels:
severity: warning
annotations:
summary: "High token validation error rate"
description: "Token validation error rate is {{ `{{` }} printf \"%.2f%%\" (mul $value 100) {{ `}}` }} (threshold: 1%)"
- alert: NextcloudMCPVectorSyncQueueHigh
expr: mcp_vector_sync_queue_size{job="{{ include "nextcloud-mcp-server.fullname" . }}"} > 100
for: 15m
labels:
severity: warning
annotations:
summary: "Vector sync queue is high"
description: "Vector sync queue size is {{ `{{` }} $value {{ `}}` }} (threshold: 100)"
- alert: NextcloudMCPQdrantSlowQueries
expr: |
histogram_quantile(0.95,
sum(rate(mcp_db_operation_duration_seconds_bucket{db="qdrant", job="{{ include "nextcloud-mcp-server.fullname" . }}"}[10m])) by (le)
) > 0.5
for: 10m
labels:
severity: warning
annotations:
summary: "Qdrant queries are slow"
description: "P95 Qdrant query latency is {{ `{{` }} printf \"%.2fs\" $value {{ `}}` }} (threshold: 0.5s)"
{{- end }}
@@ -15,5 +15,11 @@ spec:
targetPort: http
protocol: TCP
name: http
{{- if .Values.observability.metrics.enabled }}
- port: {{ .Values.observability.metrics.port }}
targetPort: metrics
protocol: TCP
name: metrics
{{- end }}
selector:
{{- include "nextcloud-mcp-server.selectorLabels" . | nindent 4 }}
@@ -0,0 +1,32 @@
{{- if and .Values.observability.metrics.enabled .Values.serviceMonitor.enabled }}
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: {{ include "nextcloud-mcp-server.fullname" . }}
namespace: {{ .Release.Namespace }}
labels:
{{- include "nextcloud-mcp-server.labels" . | nindent 4 }}
{{- with .Values.serviceMonitor.labels }}
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
selector:
matchLabels:
{{- include "nextcloud-mcp-server.selectorLabels" . | nindent 6 }}
endpoints:
- port: metrics
path: {{ .Values.observability.metrics.path }}
interval: {{ .Values.serviceMonitor.interval }}
scrapeTimeout: {{ .Values.serviceMonitor.scrapeTimeout }}
scheme: http
relabelings:
# Add namespace label
- sourceLabels: [__meta_kubernetes_namespace]
targetLabel: namespace
# Add pod label
- sourceLabels: [__meta_kubernetes_pod_name]
targetLabel: pod
# Add service label
- sourceLabels: [__meta_kubernetes_service_name]
targetLabel: service
{{- end }}
+37
View File
@@ -168,6 +168,43 @@ securityContext:
runAsNonRoot: true
runAsUser: 1000
# Observability Configuration
observability:
# Prometheus metrics
metrics:
enabled: true
port: 9090
path: /metrics
# OpenTelemetry tracing
tracing:
enabled: false
endpoint: "" # e.g., "http://opentelemetry-collector:4317"
serviceName: "nextcloud-mcp-server"
samplingRate: 1.0
# Logging configuration
logging:
format: json # "json" or "text"
level: INFO
includeTraceContext: true
# Prometheus ServiceMonitor (requires Prometheus Operator)
serviceMonitor:
enabled: false
interval: 30s
scrapeTimeout: 10s
labels: {}
# Additional labels for ServiceMonitor (e.g., for Prometheus selector)
# Example: { prometheus: kube-prometheus }
# Prometheus alert rules (requires Prometheus Operator)
prometheusRule:
enabled: false
labels: {}
# Additional labels for PrometheusRule (e.g., for Prometheus selector)
# Example: { prometheus: kube-prometheus }
service:
type: ClusterIP
port: 8000
+8 -3
View File
@@ -1172,13 +1172,15 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
checks["auth_configured"] = "error: credentials not set"
is_ready = False
# Check Qdrant status if vector sync is enabled
# Check Qdrant status if using network mode (external Qdrant service)
# In-memory and persistent modes use embedded Qdrant, no external service to check
vector_sync_enabled = (
os.getenv("VECTOR_SYNC_ENABLED", "false").lower() == "true"
)
if vector_sync_enabled:
qdrant_url = os.getenv("QDRANT_URL") # Only set in network mode
if vector_sync_enabled and qdrant_url:
try:
qdrant_url = os.getenv("QDRANT_URL", "http://qdrant:6333")
async with httpx.AsyncClient(timeout=2.0) as client:
response = await client.get(f"{qdrant_url}/readyz")
if response.status_code == 200:
@@ -1189,6 +1191,9 @@ def get_app(transport: str = "sse", enabled_apps: list[str] | None = None):
except Exception as e:
checks["qdrant"] = f"error: {str(e)}"
is_ready = False
elif vector_sync_enabled:
# Using embedded Qdrant (memory or persistent mode)
checks["qdrant"] = "embedded"
status_code = 200 if is_ready else 503
return JSONResponse(