@kubova/mcp
OfficialProvides tools for packing cargo into shipping containers, returning placements, utilization, and weight.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@kubova/mcp pack 5 pallets of books into a 20ft container"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@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.)Related MCP server: CargoEffe MCP Server
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 a list of cargo SKUs into one or more shipping containers. Returns placements, utilization, weight, and any unplaced pieces. |
| 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 |
| — | Required. Generated from the dashboard. |
License
MIT.
Available Tools
4 toolsestimate_capacityARead-only
How many complete SETS of one product fit in a single container? A product is 1+ carton types with qtyPerSet each (e.g. a table shipping as 2 cartons: top + legs). All cartons of a set ride in the SAME container. Uses real 3D packing (not just volume math) and reports the binding limit (dimension/weight/volume) per container. Omit containers to evaluate the standard 20' DC, 40' DC, 40' HC.
Inputs: product (required), containers.
generate_reportA
Generate a CAD-style PDF + 3D PNG report for a packing job. IMPORTANT: to keep the report consistent with a plan you already produced, pass the result object from your previous pack_containers call — the report then renders that exact plan instead of recomputing (which can differ run-to-run). If result is omitted, it packs from cargos + containers. Returns base64-encoded PDF + PNG per container plus the pack result.
Inputs: cargos (required), container, containers, options, +1 more.
pack_containersA
Pack a list of cargo SKUs into one or more shipping containers using the Kubova solver. Returns per-container placements with x,y,z coordinates in cm, volume utilization, weight, and any unplaced pieces.
Inputs: cargos (required), container, containers, options.
verify_keyARead-only
Verify the configured API key. Returns the key identity, scopes, and rate limit.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: capacity estimation, container packing, report generation, and API key verification; no overlap in functionality.
All tool names follow a consistent verb_noun snake_case pattern: estimate_capacity, generate_report, pack_containers, verify_key.
With 4 tools, the server is well-scoped for its packing optimization domain; each tool serves a core function without redundancy.
Covers the main workflow (estimate, pack, report) but lacks tools for managing containers or cargo definitions, though these may be handled via parameters.
Related MCP Connectors
Pack cargo into containers & onto pallets; a verifiable 3D loading plan. Free tier + REST API.
Load planning for containers, trucks & pallets in Claude & ChatGPT, with a 3D load plan in the chat.
Container load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat.
Plan optimal container & truck loads: 3D layouts, utilization, centre of gravity, crush checks.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenancePlan optimal container & truck loads: 3D layouts, right-size the container mix, and check utilization, centre of gravity, crush protection and securing across 200+ equipment types.8 npm2MIT
- AlicenseNot gradedqualityDmaintenanceConnects AI assistants to CargoEffe for automated cargo loading plan design, offering tools to manage containers, cargo items, and load plans.MIT
- AlicenseAqualityDmaintenanceEnables AI agents to pack trucks and shipping containers by generating validated 3D load plans with metrics like LDM, linear feet, and pallet positions through the Hansatic packing API.37 npmMIT
- AlicenseAqualityBmaintenanceEnables AI assistants to query and manage logistics shipment data, supporting operations like tracking, quoting, and performance analysis via nine tools backed by a demo dataset or a REST API.9253 npmMIT