vme-mcp-server 0.1.2 → 0.1.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/dist/README.md +148 -0
  2. package/package.json +2 -2
package/dist/README.md ADDED
@@ -0,0 +1,148 @@
1
+ # VME MCP Server
2
+
3
+ Transform VMware infrastructure management into conversational AI interactions with Claude.
4
+
5
+ ## Installation
6
+
7
+ ```bash
8
+ npm install -g vme-mcp-server
9
+ ```
10
+
11
+ ## Quick Start
12
+
13
+ ### 1. Configure Environment
14
+
15
+ Create a `.env` file:
16
+
17
+ ```bash
18
+ # VMware Configuration
19
+ VME_API_BASE_URL=https://your-vme-instance.com/api
20
+ VME_API_TOKEN=your-bearer-token
21
+
22
+ # Privacy Controls (Optional)
23
+ ENABLE_AI_TRAINING_DATA=false
24
+ AI_TRAINING_DATA_RETENTION_DAYS=30
25
+ ```
26
+
27
+ ### 2. Add to Claude Desktop
28
+
29
+ Add to your Claude Desktop configuration file:
30
+
31
+ **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
32
+ **Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
33
+
34
+ ```json
35
+ {
36
+ "mcpServers": {
37
+ "vme": {
38
+ "command": "vme-mcp-server"
39
+ }
40
+ }
41
+ }
42
+ ```
43
+
44
+ ### 3. Start Claude Desktop
45
+
46
+ Restart Claude Desktop. You should see the VME MCP Server tools available.
47
+
48
+ ## Usage Examples
49
+
50
+ ### Natural Language VM Creation
51
+
52
+ ```
53
+ "Create 3 Ubuntu VMs named web01 through web03 spread across cluster nodes"
54
+ ```
55
+
56
+ ```
57
+ "Create a Rocky Linux VM called db-server with 4GB RAM"
58
+ ```
59
+
60
+ ```
61
+ "Show me available VM templates and service plans"
62
+ ```
63
+
64
+ ### Supported Operations
65
+
66
+ - **Resource Discovery**: Get available service plans, OS templates, zones, and groups
67
+ - **VM Creation**: Create single or multiple VMs with intelligent naming
68
+ - **OS Resolution**: Automatically select latest stable OS versions
69
+ - **Node Distribution**: Auto-placement, spread, or specific node targeting
70
+ - **Intent Recognition**: Natural language understanding with 93%+ accuracy
71
+
72
+ ## Features
73
+
74
+ ### Intelligent Resource Discovery
75
+ - Unified API consolidating multiple VMware endpoints
76
+ - Intent-aware responses based on context
77
+ - Semantic organization of compute vs infrastructure resources
78
+
79
+ ### Natural Language Processing
80
+ - Parse complex VM provisioning requests
81
+ - Extract VM names, OS templates, sizes, zones from natural language
82
+ - Handle range patterns like "web01->web03" automatically
83
+ - Confidence scoring for reliability
84
+
85
+ ### Privacy-First Design
86
+ - Optional AI training data collection (disabled by default)
87
+ - Granular control over what data is logged
88
+ - Configurable retention periods
89
+ - All training data excluded from version control
90
+
91
+ ## Configuration
92
+
93
+ ### Required Environment Variables
94
+
95
+ | Variable | Description | Example |
96
+ |----------|-------------|---------|
97
+ | `VME_API_BASE_URL` | VMware vCenter API endpoint | `https://vcenter.company.com/api` |
98
+ | `VME_API_TOKEN` | Bearer token for authentication | `your-bearer-token` |
99
+
100
+ ### Optional Environment Variables
101
+
102
+ | Variable | Default | Description |
103
+ |----------|---------|-------------|
104
+ | `ENABLE_AI_TRAINING_DATA` | `false` | Enable interaction logging for AI improvements |
105
+ | `AI_TRAINING_DATA_RETENTION_DAYS` | `30` | How long to keep training data |
106
+ | `AI_TRAINING_DATA_FIELDS` | See docs | Which fields to include in training data |
107
+
108
+ ## Troubleshooting
109
+
110
+ ### Common Issues
111
+
112
+ **"No tools available"**
113
+ - Ensure Claude Desktop is restarted after configuration
114
+ - Check that the `vme-mcp-server` command is in your PATH
115
+ - Verify MCP configuration syntax in `claude_desktop_config.json`
116
+
117
+ **"API connection failed"**
118
+ - Verify `VME_API_BASE_URL` is correct and accessible
119
+ - Check that `VME_API_TOKEN` has sufficient permissions
120
+ - Ensure network connectivity to VMware infrastructure
121
+
122
+ **"VM creation failed"**
123
+ - Verify user permissions in VMware for VM creation
124
+ - Check that specified service plans and templates exist
125
+ - Ensure target group/zone has available resources
126
+
127
+ ### Getting Help
128
+
129
+ - Check the `.env.example` file for configuration templates
130
+ - Review error messages for specific guidance
131
+ - Ensure VMware infrastructure is accessible and properly configured
132
+
133
+ ## Architecture
134
+
135
+ This MCP server prioritizes natural language understanding over traditional REST API mappings. It provides:
136
+
137
+ - **Context-aware operations** that understand user intent
138
+ - **Intelligent resource discovery** with semantic organization
139
+ - **Role-based access** with dynamic tool schemas
140
+ - **Privacy-by-design** data collection with user control
141
+
142
+ Built with TypeScript and the Model Context Protocol for seamless Claude integration.
143
+
144
+ ## Version
145
+
146
+ Current version: 0.1.3
147
+
148
+ For development documentation and contribution guidelines, see the project repository.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "vme-mcp-server",
3
- "version": "0.1.2",
3
+ "version": "0.1.3",
4
4
  "description": "VMware vCenter MCP Server - Natural language infrastructure management for Claude",
5
5
  "main": "dist/server.js",
6
6
  "bin": {
@@ -10,7 +10,7 @@
10
10
  "build": "tsc",
11
11
  "start": "node dist/server.js",
12
12
  "dev": "tsx watch src/server.ts",
13
- "prepublishOnly": "npm run build",
13
+ "prepublishOnly": "npm run build && cp README-NPM.md dist/README.md",
14
14
  "test": "mocha tests/**/*.test.js",
15
15
  "test:unit": "mocha tests/unit/*.test.js",
16
16
  "test:integration": "mocha tests/integration/*.test.js",