MCP Microservice Debugger

Real-time Kubernetes log analysis with GitHub Copilot Claude Sonnet 4 Agent integration.

🚀 Quick Start

Option 1: Manual Setup

python startup_script.py

Enter your VM details when prompted.

Option 2: Direct Claude Integration

Use this prompt in GitHub Copilot to start debugging without running any scripts manually:

# 🚨 MCP Microservice Debug Setup

I need you to set up and run a microservice debugging system with these specs:

**System Requirements:**
- Monitor Kubernetes pod logs in real-time
- Detect: Java exceptions, OutOfMemory, SIGKILL, SIGTERM, database/kafka errors
- Parse JSON logs and group by thread ID for context analysis
- Generate debugging contexts automatically

**Connection Details:**
- VM IP: [YOUR_VM_IP]
- Username: [YOUR_USERNAME] 
- PEM Key: ./NxF-2.pem
- Pod: onc-[SERVICE_NAME]-service-0
- Namespace: onc
- Command: `kubectl logs -f onc-[SERVICE_NAME]-service-0 -n onc`

**Expected Log Format:**
```json
{
  "timestamp":"2025-09-08T11:14:10.544Z",
  "service":"inventory",
  "level":"error",
  "message":"Error message here",
  "thread":"devicenotifications_updates_5_1417"
}

Setup Instructions:

1. Install required packages: mcp, paramiko
2. Create MCP server configuration for GitHub Copilot
3. Start secure SSH connection using PEM key (no password storage)
4. Begin real-time log monitoring
5. Parse JSON logs and extract thread context
6. Detect error patterns and group related logs
7. Generate Copilot contexts with root cause analysis
8. Provide specific fix suggestions

When errors are detected:

• Group last 5 logs from same thread for context
• Analyze cascading failures
• Generate root cause analysis with confidence scores
• Create actionable fix suggestions
• Save context files: copilot_context_*.json and copilot_prompt_*.md

Please start the debugging system now and begin monitoring my microservice.

Replace [YOUR_VM_IP], [YOUR_USERNAME], and [SERVICE_NAME] with your actual values.

## 🎯 What It Does

- **Connects securely** via SSH with your PEM key
- **Monitors logs** for errors and exceptions  
- **Groups related logs** by thread ID for better context
- **Generates analysis** with root causes and fix suggestions
- **Creates Copilot contexts** automatically for debugging assistance

## 📁 Files Needed

your-project/ ├── NxF-2.pem # Your PEM key file ├── startup_script.py # Main launcher ├── mcp_debug_server.py # MCP server code └── simple_debug_client.py # Lightweight option

## 🔧 Error Detection

Automatically detects:
- Java exceptions and stack traces
- OutOfMemoryError conditions
- SIGKILL/SIGTERM signals  
- Database connection issues
- Kafka messaging problems
- Network connectivity errors

## 🤖 GitHub Copilot Commands

Once running, use these commands:

@microservice-debugger start_debug_session with vm_ip="192.168.1.100" username="admin" pem_file_path="./NxF-2.pem" pod_name="onc-inventory-service-0" namespace="onc"

@microservice-debugger get_latest_errors with count=3

@microservice-debugger stop_debug_session

## 🚨 Quick Start Prompts

**Interactive Setup (Claude asks for details):**
```markdown
@microservice-debugger I need microservice debugging setup. Please ask me for my VM IP, username, and service name, then automatically start the monitoring system.

Direct Setup (provide details immediately):

@microservice-debugger Setup debugging: VM=192.168.1.100, user=admin, service=onc-inventory-service-0, namespace=onc, key=./NxF-2.pem. Start monitoring now.

That's it! The system handles security, connects via PEM key, analyzes logs intelligently, and provides debugging contexts for GitHub Copilot automatically.