@kubova/mcp
v0.1.6
Published
Model Context Protocol (MCP) server for the Kubova 3D container loading calculator — plan container and pallet loads from any AI assistant.
Maintainers
Readme
@kubova/mcp
Model Context Protocol server for the Kubova container loading calculator.
Lets Claude, Cursor, Cline, ChatGPT, n8n, and any other MCP-aware AI agent pack shipping containers as a tool call.
Install
# Get an API key first at
# https://kubova.com/dashboard/api-keys
# (Pro plan; 14-day trial available.)Configure
Claude Code / Claude Desktop
Add to ~/.claude/settings.json (or the Claude Desktop config file):
{
"mcpServers": {
"kubova": {
"command": "npx",
"args": ["-y", "@kubova/mcp@latest"],
"env": {
"KUBOVA_API_KEY": "kbv_..."
}
}
}
}Cursor / Cline / Codex
Same JSON shape — point your MCP-aware client at the package via npx.
Tools exposed
| Tool | Purpose |
|---|---|
| pack_containers | Pack a list of cargo SKUs into one or more shipping containers. Returns placements, utilization, weight, and any unplaced pieces. |
| verify_key | Sanity-check the configured API key. Returns identity, scopes, and rate limit. |
Input schema (pack_containers)
{
cargos: [
{
id: string,
name: string,
shape?: "box" | "cylinder",
lengthCm: number,
widthCm: number,
heightCm: number,
quantity: number,
weightKg: number,
color?: string,
includeInLoading?: boolean,
allowStacking?: boolean,
allowRotation?: boolean
}
],
container?: {
id: string,
name: string,
innerLengthCm: number,
innerWidthCm: number,
innerHeightCm: number,
doorWidthCm: number,
doorHeightCm: number,
maxPayloadKg: number
},
containers?: [ /* multiple types — Kubova picks the best mix */ ],
options?: {
loadingDirection?: "floor-to-top" | "right-to-left",
maxContainers?: number
}
}Env
| Variable | Default | Notes |
|---|---|---|
| KUBOVA_API_KEY | — | Required. Generated from the dashboard. |
License
MIT.
