Monitoring - Pcnaid Documentation

Overview

Pcnaid MCP Hub provides comprehensive monitoring and logging capabilities to help you track server performance, debug issues, and maintain system health.

Real-time Monitoring

Server Status Dashboard

The Pcnaid MCP Hub dashboard provides real-time monitoring of all registered MCP servers:

Server Health: Online/offline status with automatic health checks
Response Times: Average, min, max response times per server
Request Volume: Requests per second/minute/hour
Error Rates: Success/failure ratios and error trends
Resource Usage: Memory and CPU utilization (when available)

Health Check Configuration

Configure health checks for your MCP servers:

{
  "healthCheck": {
    "enabled": true,
    "interval": 30000,
    "timeout": 5000,
    "retries": 3,
    "endpoints": {
      "ping": "/health",
      "tools": "/tools/list"
    }
  }
}

Monitoring API

Get monitoring data programmatically:

# Get server health status
curl http://localhost:3000/api/monitoring/health

# Get performance metrics
curl http://localhost:3000/api/monitoring/metrics?server=my-server&range=1h

# Get system overview
curl http://localhost:3000/api/monitoring/overview

Logging System

Log Levels

Pcnaid MCP Hub supports standard log levels:

ERROR: Critical errors requiring immediate attention
WARN: Warning conditions that should be monitored
INFO: General operational messages
DEBUG: Detailed debugging information
TRACE: Very detailed trace information

Log Configuration

Configure logging in your environment:

# Set log level
LOG_LEVEL=info

# Enable structured logging
LOG_FORMAT=json

# Log file location
LOG_FILE=/var/log/mcphub/app.log

# Enable request logging
ENABLE_REQUEST_LOGS=true

Structured Logging

Pcnaid MCP Hub uses structured logging for better analysis:

{
  "timestamp": "2024-01-20T10:30:00Z",
  "level": "info",
  "message": "MCP server request completed",
  "server": "github-mcp",
  "tool": "search_repositories",
  "duration": 245,
  "status": "success",
  "requestId": "req_123456",
  "userId": "user_789"
}

Log Management

Log Storage Options

File-based Logging

# docker-compose.yml
services:
  mcphub:
    volumes:
      - ./logs:/app/logs
    environment:
      - LOG_FILE=/app/logs/mcphub.log
      - LOG_ROTATION=daily
      - LOG_MAX_SIZE=100MB
      - LOG_MAX_FILES=7

Database Logging

{
  "logging": {
    "database": {
      "enabled": true,
      "table": "logs",
      "retention": "30d",
      "indexes": ["timestamp", "level", "server"]
    }
  }
}

External Log Services

# Syslog integration
SYSLOG_ENABLED=true
SYSLOG_HOST=localhost
SYSLOG_PORT=514
SYSLOG_FACILITY=local0

# ELK Stack integration
ELASTICSEARCH_URL=http://localhost:9200
ELASTICSEARCH_INDEX=mcphub-logs

Log Rotation

Automatic log rotation configuration:

{
  "logRotation": {
    "enabled": true,
    "maxSize": "100MB",
    "maxFiles": 10,
    "compress": true,
    "interval": "daily"
  }
}

Metrics Collection

System Metrics

Pcnaid MCP Hub collects various system metrics:

// Example metrics collected
{
  "timestamp": "2024-01-20T10:30:00Z",
  "metrics": {
    "requests": {
      "total": 1547,
      "success": 1523,
      "errors": 24,
      "rate": 12.5
    },
    "servers": {
      "online": 8,
      "offline": 2,
      "total": 10
    },
    "performance": {
      "avgResponseTime": 156,
      "p95ResponseTime": 324,
      "p99ResponseTime": 567
    },
    "system": {
      "memoryUsage": "245MB",
      "cpuUsage": "15%",
      "uptime": "72h 35m"
    }
  }
}

Custom Metrics

Add custom metrics for your use case:

// Custom metric example
const customMetric = {
  name: 'tool_usage',
  type: 'counter',
  tags: {
    server: 'github-mcp',
    tool: 'search_repositories',
    result: 'success',
  },
  value: 1,
};

// Send to metrics endpoint
await fetch('/api/monitoring/metrics', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify(customMetric),
});

Alerting

Alert Configuration

Set up alerts for critical conditions:

{
  "alerts": {
    "serverDown": {
      "condition": "server.status == 'offline'",
      "duration": "5m",
      "severity": "critical",
      "channels": ["email", "slack"]
    },
    "highErrorRate": {
      "condition": "errors.rate > 0.1",
      "duration": "2m",
      "severity": "warning",
      "channels": ["slack"]
    },
    "slowResponse": {
      "condition": "response.p95 > 1000",
      "duration": "5m",
      "severity": "warning",
      "channels": ["email"]
    }
  }
}

Notification Channels

Email Notifications

# Email configuration
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=alerts@yourcompany.com
SMTP_PASS=your-app-password
ALERT_EMAIL_TO=admin@yourcompany.com

Slack Integration

# Slack webhook
SLACK_WEBHOOK_URL=https://hooks.slack.com/services/...
SLACK_CHANNEL=#mcphub-alerts

Webhook Notifications

{
  "webhooks": [
    {
      "url": "https://your-service.com/webhooks/mcphub",
      "events": ["server.down", "error.rate.high"],
      "headers": {
        "Authorization": "Bearer your-token"
      }
    }
  ]
}

Log Analysis

Query Logs

Use the logs API to query and analyze logs:

# Get recent errors
curl "http://localhost:3000/api/logs?level=error&since=1h"

# Search logs by server
curl "http://localhost:3000/api/logs?server=github-mcp&limit=100"

# Get logs for specific request
curl "http://localhost:3000/api/logs?requestId=req_123456"

# Filter by time range
curl "http://localhost:3000/api/logs?from=2024-01-20T00:00:00Z&to=2024-01-20T23:59:59Z"

Log Aggregation

Aggregate logs for insights:

# Error summary by server
curl "http://localhost:3000/api/logs/aggregate?groupBy=server&level=error&since=24h"

# Request volume over time
curl "http://localhost:3000/api/logs/aggregate?groupBy=hour&type=request&since=7d"

Performance Monitoring

Response Time Tracking

Monitor MCP server response times:

// Response time metrics
{
  "server": "github-mcp",
  "tool": "search_repositories",
  "metrics": {
    "calls": 156,
    "avgTime": 234,
    "minTime": 89,
    "maxTime": 1205,
    "p50": 201,
    "p95": 567,
    "p99": 892
  }
}

Error Rate Monitoring

Track error rates and patterns:

# Get error rates by server
curl "http://localhost:3000/api/monitoring/errors?groupBy=server&since=1h"

# Get error details
curl "http://localhost:3000/api/monitoring/errors?server=github-mcp&details=true"

Integration with External Tools

Prometheus Integration

Export metrics to Prometheus:

# prometheus.yml
scrape_configs:
  - job_name: 'mcphub'
    static_configs:
      - targets: ['localhost:3000']
    metrics_path: '/api/monitoring/prometheus'
    scrape_interval: 30s

Grafana Dashboards

Import Pcnaid MCP Hub Grafana dashboard:

{
  "dashboard": {
    "title": "Pcnaid MCP Hub Monitoring",
    "panels": [
      {
        "title": "Server Status",
        "type": "stat",
        "targets": [
          {
            "expr": "mcphub_servers_online",
            "legendFormat": "Online"
          }
        ]
      },
      {
        "title": "Request Rate",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(mcphub_requests_total[5m])",
            "legendFormat": "Requests/sec"
          }
        ]
      }
    ]
  }
}

ELK Stack Integration

Configure Logstash for log processing:

# logstash.conf
input {
  beats {
    port => 5044
  }
}

filter {
  if [fields][service] == "mcphub" {
    json {
      source => "message"
    }

    date {
      match => [ "timestamp", "ISO8601" ]
    }
  }
}

output {
  elasticsearch {
    hosts => ["localhost:9200"]
    index => "mcphub-logs-%{+YYYY.MM.dd}"
  }
}

Troubleshooting

Common Monitoring Issues

Missing Metrics

# Check metrics endpoint
curl http://localhost:3000/api/monitoring/health

# Verify configuration
grep -r "monitoring" /path/to/config/

Log File Issues

# Check log file permissions
ls -la /var/log/mcphub/

# Verify disk space
df -h /var/log/

# Check log rotation
logrotate -d /etc/logrotate.d/mcphub

Performance Issues

# Monitor system resources
top -p $(pgrep -f mcphub)

# Check database connections
curl http://localhost:3000/api/monitoring/database

# Analyze slow queries
curl http://localhost:3000/api/monitoring/slow-queries

Debug Mode

Enable debug logging for troubleshooting:

# Enable debug mode
DEBUG=mcphub:* npm start

# Or set environment variable
export DEBUG=mcphub:monitoring,mcphub:logging

Best Practices

Log Management

Use structured logging with consistent formats
Implement proper log levels and filtering
Set up log rotation and retention policies
Monitor log file sizes and disk usage

Monitoring Setup

Configure appropriate health check intervals
Set up alerts for critical conditions
Monitor both system and application metrics
Use dashboards for visual monitoring

Performance Optimization

Index log database tables appropriately
Use log sampling for high-volume scenarios
Implement proper caching for metrics
Regular cleanup of old logs and metrics

Security Considerations

Sanitize sensitive data in logs
Secure access to monitoring endpoints
Use authentication for external integrations
Encrypt log transmission when using external services

​Overview

​Real-time Monitoring

​Server Status Dashboard

​Health Check Configuration

​Monitoring API

​Logging System

​Log Levels

​Log Configuration

​Structured Logging

​Log Management

​Log Storage Options

​File-based Logging

​Database Logging

​External Log Services

​Log Rotation

​Metrics Collection

​System Metrics

​Custom Metrics

​Alerting

​Alert Configuration

​Notification Channels

​Email Notifications

​Slack Integration

​Webhook Notifications

​Log Analysis

​Query Logs

​Log Aggregation

​Performance Monitoring

​Response Time Tracking

​Error Rate Monitoring

​Integration with External Tools

​Prometheus Integration

​Grafana Dashboards

​ELK Stack Integration

​Troubleshooting

​Common Monitoring Issues

​Debug Mode

​Best Practices

​Log Management

​Monitoring Setup

​Performance Optimization

​Security Considerations

Overview

Real-time Monitoring

Server Status Dashboard

Health Check Configuration

Monitoring API

Logging System

Log Levels

Log Configuration

Structured Logging

Log Management

Log Storage Options

File-based Logging

Database Logging

External Log Services

Log Rotation

Metrics Collection

System Metrics

Custom Metrics

Alerting

Alert Configuration

Notification Channels

Email Notifications

Slack Integration

Webhook Notifications

Log Analysis

Query Logs

Log Aggregation

Performance Monitoring

Response Time Tracking

Error Rate Monitoring

Integration with External Tools

Prometheus Integration

Grafana Dashboards

ELK Stack Integration

Troubleshooting

Common Monitoring Issues

Debug Mode

Best Practices

Log Management

Monitoring Setup

Performance Optimization

Security Considerations