Skip to content

Brimload Container Loading MCP server

com.cuberithm.mcp/container-loadingmcp.cuberithm.comstreamable-httpv1.0.2Scanned

How many identical cartons fit in a container or space, where they go, plus a 3D loading plan.

2 tools: 1 do something that can't be undone and 1 change things.

Tools: 0 delete, 1 irreversible, 1 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Brimload Container Loading MCP server can do

The Brimload Container Loading MCP server is published by mcp.cuberithm.com, a domain the MCP Registry verified. It has 2 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_feedback) and create or change data (1 tool: pack_boxes), but cannot delete data. None of its tools only reads.

1 tool brings in text other people can write (send_feedback); 1 tool can send data out of your system (send_feedback).

The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 2026, version 1.0.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

2 tools

Can't be undone 1Claude Code: ask
  • send_feedbackSend a question, suggestion, or bug report about this container-loading tool to the Zhihuo maintainers.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_feedback" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_feedback" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a question, suggestion, or bug report about this container-loading tool to the Zhihuo maintainers. Use this when the user wants to ask the tool's authors a question, suggest an improvement (e.g. another container type or output field), or report a result that looks wrong. The note reaches the Zhihuo team. Args: message: The question, suggestion, or bug report, in plain text. contact: Optional email or handle if the user would like a reply. category: Optional tag - "question", "suggestion", "bug", or "other". Returns a short confirmation string.

    Annotations the server declares

    • title: Send feedback to the Zhihuo maintainers
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
Changes things 1Claude Code: ask
  • pack_boxesCalculate how many identical boxes fit in a rectangular space, and where.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description is 2,466 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...loading plan, and - when include_image is true - the inline image too."

      What this check looks for
    Description, as the server wrote it
    Calculate how many identical boxes fit in a rectangular space, and where. The space is a shipping container, a pallet area, leftover container space, or a larger box. Give the box's L/W/H and EITHER a `container` preset OR the space's L/W/H (all in millimetres - container presets are mm). Boxes mix orientations across regions to pack densely; the plain maximum-load answer uses the exact T1 solver. Args: box_length: Box length. box_width: Box width. box_height: Box height. container: Container preset instead of explicit space dims (fills the internal usable L/W/H in mm; overrides space_* when recognised). ISO dry: 20GP 20HQ 40GP 40HQ 45GP 45HQ; NA domestic: 53HC 48HC; reefers: 20RF 40RF 40RH; EU pallet-wide: 40HQ-PW 45HQ-PW. Many aliases (20/40/45, 20ft, 40HC, 40', 40 reefer, ...). space_length: Space length (front-back). Use this OR `container`. space_width: Space width (left-right). space_height: Space height (up). count: How many boxes to load. 0 (default) loads the maximum. to_front: Anchor a partial load to the front (else the back). to_left: Anchor a partial load to the left (else the right). to_bottom: Kept for compatibility, no effect: boxes always rest on the floor. box_weight: Weight of one box (optional; same unit as max_weight). max_weight: Max total load weight (optional; 0 = no weight limit). include_image: Set true ONLY when the user wants to SEE or visualize the loading plan / 3D layout (e.g. "show the loading plan", "visualize it", "what does it look like?"). Default false is faster and lighter and still returns `image_url`, a shareable link to the 3D render. When true, the image is ALSO embedded inline (Claude Desktop and Cherry Studio display it; the claude.ai web app shows only the link either way). Returns the maximum that fits, how many were loaded, the fill rate, the region/block decomposition (each block's position, orientation, and grid), any weight limit applied, an `image_url` link to the rendered 3D loading plan, and - when include_image is true - the inline image too.

    Annotations the server declares

    • title: Pack boxes into a container or space
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:36 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.cuberithm.com/mcp: tools/list returned 2 tools to an anonymous client, including send_feedback (irreversible), pack_boxes (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description is 2,466 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...loading plan, and - when include_image is true - the inline image too."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http container-loading https://mcp.cuberithm.com/mcp
claude mcp add --transport http container-loading https://mcp.cuberithm.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__container-loading__pack_boxes",
      "mcp__container-loading__send_feedback"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as container-loading. Review it before you use it.

Capability tags behind 1 rule
  • mcp__container-loading__send_feedback untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.cuberithm.mcp/container-loading/verify?hash=ca209ef5a70a1dd2e91f4343992bef371afbaa6f1e3fc6d6cb01a624f26b2063" | jq -e '.changed == false'

Pinned hash ca209ef5a70a, from Nov 13, 2026, 00:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.cuberithm.mcp/container-loading/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.cuberithm.mcp/container-loading
[![Anlyon Radar](https://radar.anlyon.com/badge/com.cuberithm.mcp/container-loading.svg)](https://radar.anlyon.com/servers/com.cuberithm.mcp/container-loading)

Source: MCP Registry. Synced Oct 21, 2026, 17:53 UTC.

Brimload Container Loading MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Brimload Container Loading MCP server safe?

No scan can promise that. What its definitions show: 2 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Brimload Container Loading MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Brimload Container Loading MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_feedback.

What tools does the Brimload Container Loading MCP server have?

2 tools: 1 irreversible, 1 write. send_feedback and pack_boxes.

Does the Brimload Container Loading MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Brimload Container Loading MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_feedback.

Has the Brimload Container Loading MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.