Getting Started with MCP

# macOS/Linux - make sure you own the file
chmod 644 ~/Library/Application\ Support/Claude/claude_desktop_config.json

I've modified these files:
- src/services/payment/stripe-client.ts
- src/services/payment/processor.ts
- src/api/payment-routes.ts

Can you assess the deployment risk using NOFire AI?

I've analyzed your changes using NOFire AI:

Affected Services: 1 (payment-service)

Risk Assessment:
  Overall Risk: 0.82 (HIGH)
  
  Risk Breakdown:
    - Blast Radius: 0.85 (15 services affected)
    - Payment processing is on critical path
    - Dependency depth: 2 (mid-level service)
    - Recent stability: 0.70
  
  Deployment Strategy:
    ⚠️  HIGH RISK - Staged deployment mandatory
    
    1. Deploy to staging environment first
    2. Run full payment test suite
    3. Deploy to production with canary (5% traffic)
    4. Monitor for 2 hours before full rollout
    5. Notify #payments and #platform teams
    
  Critical Services in Blast Radius:
    - api-gateway (entry point)
    - billing-service (financial impact)
    - refund-service (payment flow)
    
  Recommendation: Schedule deployment during low-traffic window
  with team available for monitoring.

I'm new to this codebase. Can you use NOFire AI to show me:
1. What services we have in production
2. How the payment flow works (service dependencies)

I've queried NOFire AI about your production environment:

Services in Production (showing payment-related):
  - api-gateway (entry point for all traffic)
  - payment-service (core payment processing)
  - billing-service (invoicing and subscriptions)
  - stripe-integration-service (payment provider)
  - notification-service (payment confirmations)
  - audit-service (transaction logging)

Payment Flow Dependencies:
  
  api-gateway
    ↓ calls
  payment-service
    ↓ depends on
    ├─ stripe-integration-service (payment processing)
    ├─ billing-service (invoice creation)
    ├─ notification-service (customer emails)
    └─ audit-service (compliance logging)

Critical Services to be careful with:
  - payment-service: 15 services depend on this
  - api-gateway: Entry point, affects all traffic
  
Would you like me to explain what each service does or show
recent changes to any of them?

Using NOFire AI, what changes happened to user-service 
in the last 24 hours?

I've queried NOFire AI for recent changes to user-service:

Recent Changes (last 24 hours):
  
  1. Deployment (14 hours ago)
     - Image: user-service:v2.1.4 → v2.1.5
     - Type: Rolling update
     - Status: Completed
  
  2. Configuration Change (8 hours ago)
     - ConfigMap updated: database connection pool
     - MAX_POOL_SIZE: 20 → 50
  
  3. Pod Restart (3 hours ago)
     - 2 pods restarted due to OOMKilled
     - Memory limit hit
  
  4. Scaling Event (1 hour ago)
     - Replicas: 3 → 5
     - Reason: High CPU usage

Potential Issues:
  - Memory limit may be too low after config change
  - Connection pool increase might be causing memory pressure
  - Recent scaling event suggests ongoing performance issues

Would you like me to analyze these changes for root cause?

# AGENTS.md

## NOFire AI MCP Integration

This project uses NOFire AI for deployment risk assessment and production Knowledge.
NOFire AI MCP server is available in your IDE.

## When to use NOFire AI

**Automatically use NOFire AI in these scenarios:**

### Before Deployment (Shift-Left)
1. **Before completing any task** - Always assess deployment risk
2. **When modifying services** - Understand which production services are affected
3. **Before suggesting a merge** - Verify it's safe to deploy
4. **On refactoring** - Check blast radius and dependency impact

### Production Knowledge (Anytime)
5. **When user asks about production** - Answer with real production data
6. **During incident investigation** - Find what changed recently
7. **For onboarding new engineers** - Help understand production architecture
8. **When debugging** - Query service dependencies and recent changes

## Required Pre-Merge Workflow

Before marking any task complete or suggesting a merge:

1. Run tests: `npm test` or `pytest`
2. **Assess deployment risk** with NOFire AI:
   ```
   Call: nofireai_assess_change_impact
   Parameters: {
     "file_paths": ["src/api/payment.ts", "src/services/billing.ts"],
     "change_description": "Updated payment error handling",
     "repo_name": "company/backend"
   }
   ```
3. **Show the user** the risk score and recommendations
4. **Follow the deployment strategy** from NOFire AI

## Risk Score Interpretation

- **HIGH RISK (0.7-1.0)**: 
  Tell user: "⚠️ HIGH RISK deployment. Affects [X] critical services. 
  Recommendation: Deploy to staging first, then canary (5% → 25% → 100%).
  Team should be available. Never deploy Fridays or before holidays."

- **MEDIUM RISK (0.4-0.7)**: 
  Tell user: "⚠️ MEDIUM RISK. Affects [X] services. 
  Recommendation: Use canary deployment (10% → 50% → 100%)."

- **LOW RISK (0.0-0.4)**: 
  Tell user: "✅ LOW RISK. Standard deployment is safe."

## Available NOFire AI MCP Tools

Use these tools to query production:

### Deployment Risk & Impact
- `nofireai_assess_change_impact` - Analyze multi-file changes, get deployment strategy
- `nofireai_assess_change_risk` - Analyze single service/entity risk
- `nofireai_map_files_to_entities` - Map code files to production services
- `nofireai_analyze_blast_radius` - See cascading impact if service fails

### Service Intelligence
- `nofireai_discover_entities` - Find services, pods, deployments by name
- `nofireai_get_entity_relationships` - Show service dependencies (what calls what)
- `nofireai_get_critical_services` - List single-points-of-failure in the system

### Change Tracking & RCA
- `nofireai_get_entity_changes` - Recent changes to a service (deployments, config, restarts)
- `nofireai_analyze_entity_changes` - AI-powered root cause analysis with hypotheses
- `nofireai_get_change_timeline` - Chronological timeline with propagation detection
- `nofireai_detect_change_patterns` - Identify rollback candidates and instability

### Operational Queries
- `nofireai_get_entity_metrics` - Available metrics for a service
- `nofireai_get_dependency_depth` - How deep in the call chain is this service

## Usage Examples

**User asks:** "Add rate limiting to the payment API"

**After implementing, you should:**
```
1. Run tests
2. Call nofireai_assess_change_impact with ["api/payment.ts"]
3. NOFire returns: HIGH RISK (0.82), affects payment-service + 12 dependencies
4. Tell user: "⚠️ Changes complete. HIGH RISK deployment - affects payment 
   processing and 12 other services. Deploy to staging first, then canary 
   rollout during business hours with team available."
```

**User asks:** "What services depend on the auth-service?"

**You should:**
```
1. Call nofireai_discover_entities with name="auth-service"
2. Get entity_id from results
3. Call nofireai_get_entity_relationships with that entity_id
4. Show user the dependency graph with service names
```

**User asks:** "The API gateway was slow at 2pm. What changed?"

**You should:**
```
1. Call nofireai_discover_entities with name="api-gateway"
2. Call nofireai_analyze_entity_changes with entity_id and incident_time="2024-10-21T14:00:00Z"
3. Show user causal hypotheses with confidence scores and remediation steps
```

## When NOT to Use NOFire AI

Skip NOFire AI for:
- Documentation-only changes (*.md files)
- Test-only changes (no production code modified)
- Local development config (non-production)
- README updates, comment changes

## Critical Rule

**Always call NOFire AI before suggesting a merge that modifies production code.**

This shifts reliability left and prevents incidents before they happen.