@performance-agent/mcp-server 1.0.1 → 1.0.6

package/README.md

@@ -1,6 +1,6 @@
 # Performance Agent MCP Server
 
-A Model Context Protocol (MCP) server that provides 3 core development tools for VS Code and GitHub Copilot.
+A Model Context Protocol (MCP) server that provides 7 core development tools for VS Code and GitHub Copilot.
 
 ## 🎯 Features
 
@@ -9,6 +9,10 @@ A Model Context Protocol (MCP) server that provides 3 core development tools for
 | **generateJMXFromSwagger** | Convert Swagger/OpenAPI specs to JMeter performance test scripts |
 | **analyzeCodeComplexity** | Analyze cyclomatic complexity in local git repositories |
 | **profileFunctionPerformance** | Profile function execution time and identify slow functions |
+| **provisionAzureVM** | Provision Azure VMs from natural language descriptions |
+| **runCloudPerformanceTest** | Execute JMeter tests on Azure VMs with automated provisioning |
+| **analyzeTestResults** | Analyze JMeter test results with comprehensive metrics and VM performance data |
+| **getVMMetrics** | Fetch Azure VM performance metrics (CPU, Memory, Network, Disk) during tests |
 
 ---
 
@@ -20,6 +24,11 @@ A Model Context Protocol (MCP) server that provides 3 core development tools for
 - Git
 - VS Code with GitHub Copilot
 
+### Platform Support
+✅ **Windows** - Fully supported  
+✅ **macOS** - Fully supported  
+✅ **Linux** - Fully supported  
+
 ### Install Dependencies
 
 ```bash
@@ -28,6 +37,8 @@ npm install
 npm run build
 ```
 
+> **Note:** Build script is cross-platform and works on Windows, macOS, and Linux.
+
 ### Optional: Enhanced Python Analysis
 
 For more accurate Python complexity analysis:
@@ -46,7 +57,18 @@ pip install radon
 
 For local development and testing:
 
-#### Step 1: Create/Edit `.vscode/mcp.json`
+#### Step 1: Configure Azure OpenAI
+
+Create `.env` file in the mcp-server directory:
+
+```bash
+OPENAI_ENDPOINT=https://your-openai-endpoint.openai.azure.com
+OPENAI_API_KEY=your-api-key-here
+OPENAI_DEPLOYMENT=gpt-4
+OPENAI_API_VERSION=2024-02-15-preview
+```
+
+#### Step 2: Create/Edit `.vscode/mcp.json`
 
 ```json
 {
@@ -57,21 +79,16 @@ For local development and testing:
         "/Users/amanraj/Documents/CodeWorkspace/Performance-Agent/mcp-server/dist/index.js"
       ],
       "env": {
-        "PERFORMANCE_AGENT_API_URL": "http://127.0.0.1:8000"
+        "OPENAI_ENDPOINT": "https://your-openai-endpoint.openai.azure.com",
+        "OPENAI_API_KEY": "your-api-key-here",
+        "OPENAI_DEPLOYMENT": "gpt-4"
       }
     }
   }
 }
 ```
 
-> **Replace** `/absolute/path/to/` with your actual path.
-
-#### Step 2: Start Backend API (for JMX generation)
-
-```bash
-cd /path/to/Performance-Agent
-python app.py
-```
+> **Replace** `/absolute/path/to/` with your actual path and add your Azure OpenAI credentials.
 
 #### Step 3: Restart VS Code
 
@@ -99,7 +116,7 @@ npm publish --access public
 **User Installation:**
 
 ```bash
-npm install -g @performance-agent/mcp-server
+npm install -g @performance-agent/mcp-server@latest
 ```
 
 **User Configuration (`.vscode/mcp.json`):**
@@ -110,8 +127,11 @@ npm install -g @performance-agent/mcp-server
     "performance-agent": {
       "command": "performance-agent-mcp",
       "env": {
-        "PERFORMANCE_AGENT_API_URL": "https://your-backend.azure.com",
-        "PERFORMANCE_AGENT_API_KEY": "your-api-key"
+        "OPENAI_ENDPOINT": "https://your-openai-endpoint.openai.azure.com",
+        "OPENAI_API_KEY": "your-api-key-here",
+        "OPENAI_DEPLOYMENT": "gpt-5",
+        "OPENAI_API_VERSION": "2024-12-01-preview",
+        "DEBUG": "false"
       }
     }
   }
@@ -282,6 +302,301 @@ Profile functions in my last commit
 
 ---
 
+### Tool 4: Provision Azure VM
+
+**In GitHub Copilot Chat:**
+
+```
+Create a large Ubuntu VM in East US for my web server
+```
+
+```
+Provision a Windows 2022 VM with 4 cores and 16GB RAM
+```
+
+```
+Set up a GPU VM for machine learning with 100GB disk
+```
+
+**Natural Language Examples:**
+
+| Request | Resulting Configuration |
+|---------|------------------------|
+| "small Ubuntu VM in westeurope" | Standard_B1ms, Ubuntu 22.04, West Europe |
+| "large Windows server with RDP" | Standard_D4s_v3, Windows 2022, Port 3389 open |
+| "GPU VM for ML with public IP" | Standard_NC6s_v3, Ubuntu 22.04, NVIDIA V100 |
+| "medium web server with auto-shutdown at 7pm" | Standard_D2s_v3, Ports 80/443, Auto-shutdown 19:00 |
+| "spot instance for budget testing" | Spot priority, cost savings up to 90% |
+
+**Parameters:**
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| `description` | string | No* | - | Natural language description of VM |
+| `config` | object | No* | - | Structured VM configuration |
+| `method` | string | No | `dry-run` | `dry-run`, `terraform`, `azure-cli` |
+| `generateTerraform` | boolean | No | `true` | Generate Terraform files |
+| `outputPath` | string | No | `cwd` | Directory for generated files |
+
+*Either `description` or `config` is required
+
+**VM Size Presets:**
+
+| Preset | Size | CPUs | RAM | Best For |
+|--------|------|------|-----|----------|
+| `small` | Standard_B1ms | 1 | 2GB | Testing, dev |
+| `medium` | Standard_D2s_v3 | 2 | 8GB | General purpose |
+| `large` | Standard_D4s_v3 | 4 | 16GB | Production |
+| `xlarge` | Standard_D8s_v3 | 8 | 32GB | High performance |
+| `compute-optimized` | Standard_F4s_v2 | 4 | 8GB | CPU-intensive |
+| `memory-optimized` | Standard_E4s_v3 | 4 | 32GB | Databases, caches |
+| `gpu` | Standard_NC6s_v3 | 6 | 112GB | ML, AI, rendering |
+
+**Supported Operating Systems:**
+
+| OS | Keyword |
+|----|---------|
+| Ubuntu 22.04 LTS | `ubuntu`, `ubuntu-22.04`, `jammy` |
+| Ubuntu 20.04 LTS | `ubuntu-20.04`, `focal` |
+| Debian 11 | `debian`, `bullseye` |
+| RHEL 8 | `rhel`, `red hat`, `centos` |
+| Windows Server 2022 | `windows`, `windows-2022` |
+| Windows Server 2019 | `windows-2019` |
+
+**Example Response (dry-run):**
+
+```json
+{
+  "success": true,
+  "vmName": "my-web-server",
+  "resourceGroup": "rg-my-web-server",
+  "region": "eastus",
+  "vmSize": "Standard_D4s_v3",
+  "provisioningState": "DryRun",
+  "terraformGenerated": true,
+  "terraformPath": "/path/to/terraform/my-web-server",
+  "estimatedCost": {
+    "hourly": 0.192,
+    "monthly": 140.16,
+    "currency": "USD"
+  },
+  "message": "Dry run completed. Terraform files generated."
+}
+```
+
+**Generated Terraform Structure:**
+
+```
+terraform/my-web-server/
+├── main.tf              # Complete Terraform configuration
+├── terraform.tfvars.example  # Variables template
+└── README.md            # Quick start guide
+```
+
+---
+
+### Tool 5: Run Cloud Performance Test
+
+**In GitHub Copilot Chat:**
+
+```
+Run performance test with my JMX script
+```
+
+```
+Execute load test on Azure VM using performance-agent_generated.jmx
+```
+
+**Parameters:**
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| `jmx_file_path` | string | Yes | - | Path to JMeter JMX script |
+| `vm_size` | string | No | `Standard_B1ms` | Azure VM size for test execution |
+| `region` | string | No | `eastus` | Azure region for VM |
+| `resource_group` | string | No | Auto-generated | Resource group name |
+| `cleanup_after` | boolean | No | `true` | Delete VM after test |
+
+**Example Response:**
+
+```json
+{
+  "success": true,
+  "vmName": "perf-test-vm",
+  "vmPublicIP": "20.10.30.40",
+  "resourceGroup": "rg-perf-test-agent",
+  "resultsPath": ".perf-output/test-results/test-2026-01-24T10-54-02-394Z/",
+  "summary": {
+    "totalRequests": 1000,
+    "successRate": 99.5,
+    "avgResponseTime": 245,
+    "throughput": 50
+  }
+}
+```
+
+---
+
+### Tool 6: Analyze Test Results
+
+**In GitHub Copilot Chat:**
+
+```
+Analyze my test results
+```
+
+```
+Show me performance metrics from the last test
+```
+
+**Parameters:**
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `result_file_path` | string | Yes | Path to JMeter results.jtl file |
+| `resource_group` | string | No | Azure resource group for VM metrics |
+| `vm_name` | string | No | VM name for infrastructure metrics |
+| `test_start_time` | string | No | ISO 8601 timestamp for metrics time range |
+| `test_end_time` | string | No | ISO 8601 timestamp for metrics time range |
+
+**Example Response:**
+
+```json
+{
+  "success": true,
+  "summary": {
+    "totalRequests": 1000,
+    "successfulRequests": 995,
+    "errorRate": 0.5,
+    "avgResponseTime": 245.2,
+    "p95ResponseTime": 450,
+    "p99ResponseTime": 680,
+    "throughput": 50.2
+  },
+  "vmMetrics": {
+    "available": true,
+    "cpuUsage": { "avg": 45.2, "max": 78.5 },
+    "memoryUsage": { "avg": 62.3, "max": 85.1 },
+    "networkIO": { "inboundMBps": 12.5, "outboundMBps": 8.3 },
+    "diskIO": { "readMBps": 25.1, "writeMBps": 15.7 }
+  },
+  "insights": [
+    "✅ All requests completed successfully with 0.5% error rate",
+    "✅ Good response times - API performance is acceptable",
+    "⚠️ WARNING: VM Memory Usage - Avg 62.3%, Max 85.1% (High)"
+  ],
+  "recommendations": [
+    "⚠️ Memory usage is high - consider increasing VM memory"
+  ]
+}
+```
+
+**VM Metrics Analysis:**
+
+The tool automatically analyzes infrastructure performance and provides:
+- 🟢 **Normal** - Metrics within acceptable ranges
+- 🟠 **Warning** - Approaching limits (CPU >70%, Memory >80%)
+- 🔴 **Critical** - Exceeding limits (CPU >80%, Memory >90%)
+
+---
+
+### Tool 7: Get VM Metrics
+
+**In GitHub Copilot Chat:**
+
+```
+Get VM metrics for perf-test-vm
+```
+
+```
+Show me CPU and memory usage during the test
+```
+
+**Parameters:**
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| `resource_group` | string | Yes | - | Azure resource group name |
+| `vm_name` | string | No | Auto-detected | VM name (detected from Terraform) |
+| `time_range` | string | No | `1h` | `1h`, `6h`, `24h`, or `custom` |
+| `start_time` | string | If custom | - | ISO 8601 start timestamp |
+| `end_time` | string | If custom | - | ISO 8601 end timestamp |
+| `metrics` | array | No | `['all']` | `['cpu', 'memory', 'network', 'disk']` or `['all']` |
+
+**Example Response:**
+
+```json
+{
+  "success": true,
+  "resourceGroup": "rg-perf-test-new",
+  "vmName": "perf-test-vm",
+  "timeRange": "1h",
+  "metrics": {
+    "cpu": {
+      "average": 45.2,
+      "maximum": 78.5,
+      "minimum": 12.3,
+      "unit": "%",
+      "status": "normal",
+      "analysis": "✅ CPU usage averaged 45.2% - Healthy utilization"
+    },
+    "memory": {
+      "average": 62.3,
+      "maximum": 85.1,
+      "minimum": 45.7,
+      "unit": "%",
+      "status": "warning",
+      "analysis": "⚠️ WARNING: Memory usage at 62.3% - VM is running high on memory"
+    },
+    "network": {
+      "bytesIn": { "total": 1250.5, "average": 12.5, "unit": "MB" },
+      "bytesOut": { "total": 830.2, "average": 8.3, "unit": "MB" },
+      "status": "normal"
+    },
+    "disk": {
+      "readBytes": { "total": 2510.3, "average": 25.1, "unit": "MB" },
+      "writeBytes": { "total": 1570.8, "average": 15.7, "unit": "MB" },
+      "iops": { "read": 450, "write": 320 },
+      "status": "normal"
+    }
+  },
+  "anomalies": [
+    "⚠️ WARNING: Memory usage at 62.3% - VM is running high on memory"
+  ],
+  "summary": "⚠️ VM Performance Issues Detected: 1 anomaly found"
+}
+```
+
+**Raw Metrics Debugging:**
+
+All raw Azure Monitor data is saved to `.perf-output/vm-metrics-raw/<vm-name>-<timestamp>/` for verification:
+- `vm-details.json` - Complete VM configuration (size, SKU)
+- `cpu-raw.json` - Raw CPU metrics from Azure Monitor
+- `memory-raw.json` - Raw memory data with calculation details (VM size, total memory bytes)
+- `network-in-raw.json` / `network-out-raw.json` - Network traffic data
+- `disk-read-raw.json` / `disk-write-raw.json` - Disk I/O data
+- `summary.json` - Processed metrics with calculation formulas
+
+**Memory Calculation Formula:**
+```
+Memory Usage % = ((Total Memory Bytes - Available Memory Bytes) / Total Memory Bytes) × 100
+
+Example: Standard_B1ms (2GB total)
+- Available: 700 MB
+- Used: 1348 MB (66.4%)
+```
+
+**VM Metrics Thresholds:**
+
+| Metric | Normal | Warning | Critical |
+|--------|--------|---------|----------|
+| **CPU** | < 70% | 70-80% | > 80% |
+| **Memory** | < 80% | 80-90% | > 90% |
+| **Network** | < 100 MB/s | 100-500 MB/s | > 500 MB/s |
+| **Disk I/O** | < 50 MB/s | 50-100 MB/s | > 100 MB/s |
+
+---
+
 ## 📊 Complexity Thresholds
 
 | Score | Risk Level | Recommendation |
@@ -346,6 +661,38 @@ Profile the performance of my functions
 
 Identify slow functions and get optimization recommendations.
 
+### Azure Infrastructure Provisioning
+
+```
+Create a large Ubuntu VM in East US with public IP and ports 22, 80, 443 open
+```
+
+Generate Terraform/CLI commands to provision Azure VMs.
+
+### Cloud Performance Testing
+
+```
+Run performance test with performance-agent_generated.jmx
+```
+
+Execute JMeter test on Azure VM with automated provisioning and cleanup.
+
+### Infrastructure Monitoring
+
+```
+Get VM metrics for my test VM
+```
+
+Monitor CPU, memory, network, and disk usage during performance tests to identify bottlenecks.
+
+### Test Result Analysis
+
+```
+Analyze my test results
+```
+
+Get comprehensive performance analysis with VM infrastructure metrics, insights, and actionable recommendations.
+
 ---
 
 ## 🏗️ Architecture
@@ -370,6 +717,22 @@ Identify slow functions and get optimization recommendations.
 │  │ Profiler  │  │
 │  └───────────┘  │
 │  ┌───────────┐  │
+│  │ Azure VM  │──┼──► Generates Terraform/Azure CLI
+│  │ Provision │  │
+│  └───────────┘  │
+│  ┌───────────┐  │
+│  │Cloud Test │──┼──► Provisions VM, Runs JMeter, Fetches Results
+│  │ Executor  │  │
+│  └───────────┘  │
+│  ┌───────────┐  │
+│  │ VM Metrics│──┼──► Azure Monitor API (CPU/Memory/Network/Disk)
+│  │  Fetcher  │  │
+│  └───────────┘  │
+│  ┌───────────┐  │
+│  │ Test      │──┼──► Analyzes JTL + VM Metrics
+│  │ Analyzer  │  │
+│  └───────────┘  │
+│  ┌───────────┐  │
 │  │ JMX Gen   │──┼──► Backend API (Flask)
 │  └───────────┘  │
 └─────────────────┘
@@ -391,11 +754,21 @@ mcp-server/
 │       │   └── analyzers/
 │       │       ├── python-analyzer.ts     # Python (radon)
 │       │       └── javascript-analyzer.ts # JS/TS (escomplex)
-│       └── function-profiler/
-│           ├── index.ts            # Profiler entry point
-│           ├── types.ts            # TypeScript interfaces
-│           ├── python-profiler.ts  # Python (timeit)
-│           └── javascript-profiler.ts # JS/TS profiler
+│       ├── function-profiler/
+│       │   ├── index.ts            # Profiler entry point
+│       │   ├── types.ts            # TypeScript interfaces
+│       │   ├── python-profiler.ts  # Python (timeit)
+│       │   └── javascript-profiler.ts # JS/TS profiler
+│       ├── azure-infra/
+│       │   ├── index.ts            # Azure provisioner entry point
+│       │   ├── types.ts            # VM configuration types
+│       │   ├── config-parser.ts    # Natural language parser
+│       │   └── terraform-generator.ts # Terraform/CLI generator
+│       └── cloud-executor/
+│           ├── index.ts            # Cloud test executor
+│           ├── vm-metrics.ts       # Azure Monitor metrics fetcher
+│           ├── result-analyzer.ts  # Test result analyzer with VM metrics
+│           └── test-executor.ts    # JMeter test execution on Azure
 ├── dist/                           # Compiled JavaScript
 ├── package.json
 ├── tsconfig.json
@@ -458,18 +831,20 @@ curl http://localhost:8000/health
 ## 🔐 Security
 
 - All complexity analysis runs **locally** - no code sent externally
-- Backend API keys stored in environment variables
-- HTTPS in production for JMX generation API calls
+- Azure OpenAI credentials stored in environment variables
+- HTTPS for Azure OpenAI API calls
 - No sensitive data logged
 
 ---
 
 ## 📝 Environment Variables
 
-| Variable | Local | Production | Description |
-|----------|-------|------------|-------------|
-| `PERFORMANCE_AGENT_API_URL` | `http://localhost:8000` | `https://your-api.azure.com` | Backend API URL |
-| `PERFORMANCE_AGENT_API_KEY` | _(empty)_ | Your API key | Authentication key |
+| Variable | Required | Example | Description |
+|----------|----------|---------|-------------|
+| `OPENAI_ENDPOINT` | ✅ Yes | `https://your-openai.openai.azure.com` | Azure OpenAI endpoint URL |
+| `OPENAI_API_KEY` | ✅ Yes | `your-api-key-here` | Azure OpenAI API key |
+| `OPENAI_DEPLOYMENT` | ✅ Yes | `gpt-4` | Azure OpenAI deployment name |
+| `OPENAI_API_VERSION` | No | `2024-02-15-preview` | Azure OpenAI API version |
 
 ---
 

package/dist/index.d.ts

@@ -2,12 +2,22 @@
 /**
  * Performance Agent MCP Server
  *
- * This MCP server provides 3 core tools:
+ * This MCP server provides 12 core tools:
  * 1. Generate JMX scripts from Swagger/OpenAPI specifications
- * 2. Analyze code complexity in local git repositories
- * 3. Profile function execution time and identify slow functions
+ * 2. Prepare JMX for testing (workflow tool)
+ * 3. Analyze code complexity in local git repositories
+ * 4. Profile function execution time and identify slow functions
+ * 5. Provision Azure infrastructure (VMs) from natural language descriptions
+ * 6. List Azure subscriptions for user selection
+ * 7. Set active Azure subscription
+ * 8. List Azure resource groups for reuse
+ * 9. Run end-to-end cloud performance tests
+ * 10. Get VM size recommendations for JMX scripts
+ * 11. Cleanup Azure test infrastructure (Terraform destroy)
+ * 12. Analyze test results with VM metrics
+ * 13. Get Azure VM performance metrics (CPU, Memory, Network, Disk)
  *
- * Focused on local development and code quality.
+ * Focused on local development, code quality, cloud performance testing, and infrastructure monitoring.
  */
 export {};
 //# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;;;;;;;GASG"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;;;;;;;;;;;;;;;;;GAmBG"}