Skip to main content
Glama
Sign In
hansatic-mcp

hansatic-mcp

by 1aleksa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Hansatic MCP — load planning for AI agents

Give your AI agent the ability to pack trucks and shipping containers. This MCP server wraps the Hansatic packing API: submit a cargo manifest, get back a physically valid layout — placements with rotation, stacking, fragility, weight and axle constraints respected — plus the freight billing metrics that matter: LDM (loading meters), linear feet, and EUR pallet positions.

"Pack 14 machine crates and 8 EUR pallets into a 13.6m curtainsider" → a validated 3D load plan with 5.25 LDM, in one tool call.

Setup

  1. Get an API key (free): hansatic.com → sign in → click your name → API → Generate key. Every account includes 25 free sandbox packs/month — no subscription needed to try it.

  2. Add the server to your MCP client:

Claude Code

claude mcp add hansatic -e HANSATIC_API_KEY=hk_live_... -- npx -y hansatic-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "hansatic": {
      "command": "npx",
      "args": ["-y", "hansatic-mcp"],
      "env": { "HANSATIC_API_KEY": "hk_live_..." }
    }
  }
}

Cursor (.cursor/mcp.json) — same shape as Claude Desktop.

Related MCP server: loadingmcp-mcp

Tools

Tool

What it does

pack_cargo

Optimize a cargo manifest into a vehicle. Async under the hood; returns the finished layout + metrics in one call (typically 5–30s). Production accounts get a plan_url — the layout opens in Hansatic's 3D editor.

list_vehicles

All built-in trucks, trailers and containers with interior dimensions and payload — the valid vehicle codes.

check_job

Poll a job by id (only for very large manifests that outlive the tool timeout).

Notes

  • Units: metric (mm/kg) by default; pass units: "imperial" for in/lb — results come back in the same units.

  • Sandbox vs production: non-enterprise keys sandbox automatically (full result, nothing persisted). Enterprise keys create a real plan in the workspace, editable at the returned plan_url.

  • The engine is validated continuously against real dispatcher layouts — see how the algorithm is measured.

  • REST API, OpenAPI spec and full docs: hansatic.com/en/docs

MIT licensed. The optimization engine runs server-side at hansatic.com.

Available Tools

3 tools
check_jobA

Check the status/result of a packing job by id (only needed if pack_cargo timed out on a very large manifest).

Inputs: job_id (required).

list_vehiclesA

List all available trucks, trailers and shipping containers with their interior dimensions (mm) and max payload (kg). Use the returned codes as the "vehicle" argument of pack_cargo.

Inputs: no named parameters.

pack_cargoA

Optimize how cargo is loaded into a truck, trailer or shipping container. Returns a physically valid layout (placements with x/y/z and rotation, respecting stacking, fragility, weight and axle constraints) plus the freight billing metrics: LDM (loading meters), linear feet, EUR pallet positions and total weight. Submits an async job and waits for the result — typically 5-30 seconds. Use list_vehicles first if you are unsure of the vehicle code.

Inputs: items (required), vehicle (required), name, units, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.5/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: list_vehicles retrieves vehicle options, pack_cargo submits an optimization job, and check_job monitors that job. There is no overlap or ambiguity.

    Naming Consistency5/5

    All three tools follow a consistent verb_noun pattern with snake_case: check_job, list_vehicles, pack_cargo. The naming is predictable and clear.

    Tool Count5/5

    With only 3 tools, the scope is narrow but well-defined. Each tool serves an essential step in the cargo packing workflow without unnecessary extras.

    Completeness5/5

    The domain of cargo packing is fully covered: listing available vehicles, computing an optimal pack, and checking on an async job. No obvious gaps are present.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • @kubova/mcp

      @kubova/mcpofficial

      Kubova-com
      A
      license
      A
      quality
      D
      maintenance
      Lets AI agents pack shipping containers using the Kubova calculator, with tools for container loading and API key verification.
      4
      12 npm
      MIT

    • loadingmcp-mcp

      lxxmng
      A
      license
      Not graded
      quality
      C
      maintenance
      Plan 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 npm
      2
      MIT

    • 3dpacking-mcp

      OnurGumus
      A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to plan container and truck loads from plain-English shipment descriptions, returning fitted containers, utilization, non-fitting items, and interactive 3D load plans.
      1
      114 npm
      MIT

    • Load Planner MCP

      bayraak
      A
      license
      A
      quality
      C
      maintenance
      Enables optimal freight-mode selection (air, sea-LCL, full container) by solving 3D bin-packing, cost optimization, and delivery-risk analysis behind two tools: solve for deterministic planning and explain for hallucination-proof natural-language narration of results.
      2
      MIT