MCP integration

Plug Kubova into Claude, Cursor, Cline, ChatGPT, or any MCP-aware AI agent. Pack containers with a single tool call.

1Get an API key

MCP access needs the same Pro API key as the REST API. A 14-day trial is available.

2Configure your client

Drop this into your MCP client's settings file. The npx command downloads the @kubova/mcp package on first run.

Claude Code · Claude Desktop · Cursor · Cline:

{
  "mcpServers": {
    "kubova": {
      "command": "npx",
      "args": ["-y", "@kubova/mcp@latest"],
      "env": {
        "KUBOVA_API_KEY": "kbv_..."
      }
    }
  }
}

Claude Code: ~/.claude/settings.json · Claude Desktop: claude_desktop_config.json · Cursor: ~/.cursor/mcp.json

3Talk to it

Restart your client, then ask the AI anything that needs container packing:

> Pack 20 boxes of 50x40x30 cm into a 40HC container.
> What's the utilization?

The agent will call the pack_containers tool, render placements, and explain the result.

Tools exposed

Tool	Purpose
pack_containers	Pack a list of SKUs into one or more containers. Returns per-container placements with x,y,z and utilization.
verify_key	Sanity check the API key — returns identity, scopes, and rate limit.

Source

MCP server source lives in the Kubova monorepo under services/mcp-server.