Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者提供的说明(英文原文)
Plan optimal container & truck loads: 3D layouts, utilization, centre of gravity, crush checks.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.loadingmcp.com/mcp在终端中运行这条命令
claude mcp add --transport http container-loading https://mcp.loadingmcp.com/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"container-loading": {
"url": "https://mcp.loadingmcp.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"container-loading": {
"type": "http",
"url": "https://mcp.loadingmcp.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.loadingmcp.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 lxxmng 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.3.0)于33天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Plan container & truck loads across 200+ equipment types from Claude, Cursor, or any MCP client.
LoadingMCP is a container load-planning MCP server that lets an AI assistant compute 3D load plans, right-size the container mix, and check that a load is legal and safe to ship. It covers 200+ equipment types (containers, trucks, ULDs, pallets) and returns volume & payload utilization, centre of gravity, crush & securing checks, VGM, axle load, and CTU/IMDG compliance signals. It runs as a hosted remote server, so there is nothing to self-host.
Ask your AI: *"Plan a 40HC load for these pallets"* or *"What's the cheapest container mix for 48 m³ at 19 t?"*
Sister product to TrackingMCP (ocean container tracking) and SchedulesMCP (sailing schedules & reliability).
| Tool | What it does |
|---|---|
list_equipment | List the container, truck, ULD, and pallet types LoadingMCP can plan into, with internal dimensions (mm) and max payload (kg). |
suggest_containers | Quick volume + weight estimate of how many of which container to use, given total cargo volume (m³) and weight (kg). |
plan_load | Compute a 3D load plan: equipment used, utilization (volume & payload %), centre of gravity, crush-protection violations, and a securing checklist. Cargo type drives realism (drums/pipes hex-nest, big bags load on top). Omit the equipment code to auto right-size. |
export_plan | Export a machine-readable loading work order: numbered stuffing sequence (which SKU, where, in what order and orientation), securing/bracing actions, declarable VGM / axle / CoG figures, and an optional retailer (Amazon FBA / Walmart) inbound-packaging check. |
The server is hosted at https://mcp.loadingmcp.com/mcp. Try it with zero signup using the public demo key lmcp_demo_public (clearly-labelled synthetic plans from the offline preview packer). A real API key runs the full 200+ equipment catalogue and the production PackingSolver optimizer.
{
"mcpServers": { "container-loading": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.loadingmcp.com/mcp", "--header", "Authorization: Bearer lmcp_demo_public"] } } }
{
"mcpServers": { "container-loading": { "url": "https://mcp.loadingmcp.com/mcp", "headers": { "Authorization": "Bearer lmcp_demo_public" } } } }
Replace lmcp_demo_public with a key from loadingmcp.com/mcp. Don't add "type": "streamable-http" — Claude Desktop rejects unknown config fields; Cursor/Windsurf infer transport from url. Registry ID: io.github.lxxmng/container-loading.
Demo output is synthetic and clearly labelled. export_plan is decision support to help you MEET published retailer/carrier specs — verify in your own portal; it is not a retailer certification.
MIT