SMB AI Command Platform MCP Server
# SMB AI Command Platform - MCP Server
Model Context Protocol (MCP) server for the SMB AI Command Platform, enabling AI assistants to interact with platform APIs.
## Overview
This MCP server provides tools for AI assistants (like Claude) to:
- Query business data
- Create and manage tasks
- Access connector data
- Interact with dashboards
- Monitor security status
## Installation
```bash
npm install
npm run build
```
## Configuration
Create a `.env` file based on `.env.example`:
```env
SMB_API_URL=http://localhost:3000
SMB_API_KEY=your-api-key
```
## Usage
### With Claude Desktop
Add to your Claude Desktop config (`~/.claude/claude_desktop_config.json`):
```json
{
"mcpServers": {
"smb-platform": {
"command": "node",
"args": ["/path/to/binelekv2-mcp-server/build/index.js"],
"env": {
"SMB_API_URL": "http://localhost:3000",
"SMB_API_KEY": "your-api-key"
}
}
}
}
```
### Development
```bash
npm run dev
```
## Available Tools
| Tool | Description |
|------|-------------|
| `smb_query` | Query data using natural language |
| `smb_create_task` | Create a new task |
| `smb_list_tasks` | List tasks with filters |
| `smb_get_connectors` | Get connected services |
| `smb_get_dashboard` | Get dashboard data |
| `smb_get_security_status` | Get security posture |
## Structure
```
src/
├── index.ts # MCP server entry point
├── client.ts # API client for SMB platform
└── tools/ # Tool implementations
```
## Related Repositories
- [binelekv2-smb-platform-backend](https://github.com/k5tuck/binelekv2-smb-platform-backend)
- [binelekv2-smb-platform-frontend](https://github.com/k5tuck/binelekv2-smb-platform-frontend)
- [binelekv2-docs](https://github.com/k5tuck/binelekv2-docs)
## License
MIT
TDQS
Scored across 16 tools
Each tool targets a distinct resource and action, e.g., smb_create_automation vs smb_list_automations vs smb_run_automation, with no overlapping purposes. The descriptions clearly differentiate between dashboards, metrics, connectors, security, product tracking, search, and query.
All tools follow the consistent pattern 'smb_verb_noun' using snake_case (e.g., smb_list_connectors, smb_sync_connector). The verbs are descriptive (create, get, list, run, sync, track) and uniformly applied, making the tool set predictable.
With 16 tools, the count is well-scoped for an SMB AI platform covering automation, dashboards, metrics, connectors, security, product tracking, search, and query. Each tool earns its place without redundancy or excess.
The tool set covers core CRUD and operational workflows for automation, dashboards, metrics, connectors, security, and product tracking. Minor gaps exist (e.g., no update/delete for automations, no user management beyond listing), but the surface is largely complete for common SMB tasks.