原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Orrery

作者:Sagargupta16版本 0.12.2i★ –i在你的电脑上运行
注册名称io.github.Sagargupta16/orrery

安装

概览

作者提供的说明(英文原文)

Architecture diagrams with official AWS, Azure, GCP and Kubernetes icons, to SVG, PNG and draw.io

PopNx MCP 的三大支柱

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。

它能帮你做什么

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。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 开发者工具

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

你需要

  • npm已安装 Node.js(用于 npx 命令)

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 …”。

下载作者的 .mcpb 文件

链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。

在终端中运行这条命令

claude mcp add orrery -- npx -y @sagargupta1610/orrery mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "orrery": {
      "command": "npx",
      "args": [
        "-y",
        "@sagargupta1610/orrery",
        "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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "orrery": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@sagargupta1610/orrery",
        "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。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

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。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

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8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Sagargupta16 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“开发者工具”中的其他服务器比较i

  • 星标数多于此分类中其他 5547 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 5547 个服务器的 74% 更新
  • 基础检查结果等于或优于此分类中其他 5547 个服务器的 100%

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。

常见问题

Orrery 安全吗?

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。

它需要哪些密钥或代码?

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。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.12.2)于6天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js, MCPB。

有什么可以替代它?

同一分类中有:GitHub, Desktop Commander, Cloudflare MCP

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:↓ 每周下载量i★ 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

GitHub

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

作者:github广泛使用★ 3.4万5天前更新

电脑或云端

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者:wonderwhy-er广泛使用↓ 71万/周★ 1万17天前更新

在你的电脑上运行

Cloudflare MCP

Cloudflare MCP servers

作者:cloudflare广泛使用★ 444614个月前更新

在云端运行✓ mcp.cloudflare.com

作者的 README

打开 README

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。

orrery

Animated architecture and system design diagrams with official AWS, Azure, Google Cloud, Kubernetes, GitHub and IBM icons.

One YAML spec in; SVG, PNG, editable draw.io, a React component and an HTML viewer out.

[sagargupta.online/orrery](https://sagargupta.online/orrery/): every example in light and dark, with its spec and downloads.

The diagram above is docs/hero.yaml: 40 lines of YAML, laid out and rendered by orrery in its default stage skin: the groups light, then the tiles, then a packet with a comet tail runs the main path in order, lighting each line behind it, on a loop. Every picture in this README is the stage skin; skin: classic (or --skin classic) draws the same layout in each vendor's own diagram style, with a packet along every edge. GitHub keeps the animation; the PNG of the same spec is a still frame.

What you get

  • Official, current icons only. 18,300 icons: AWS (810), Azure (636), Google Cloud (233), Kubernetes (40), GitHub Octicons (408) and IBM Carbon (2,783), plus 5,558 tech logos, 6,305 neutral symbols and Phosphor (1,527) in six weights for system design and business flows; your own SVGs work too, as local: icons drawn and checked with orrery icons new and icons check. The cloud packs are rebuilt from each vendor's own download, pinned by checksum. Google Cloud products get the icon Google's 2026 guide assigns them; deprecated sets and unofficial redraws of cloud icons are left out.
  • Official conventions. AWS groups follow the AWS Architecture Icons deck (borders, dashes, corner tiles, label placement, open arrowheads, numbered callouts); Google Cloud and Azure groups are measured from their own reference diagrams. Every value cites its source in styles.md.
  • Business flows too. kind: turns the same spec into an ISO 5807 flowchart, a BPMN 2.0 process with pools, lanes and message flows, a UML state machine, an org chart, a two-sided mind map or a customer journey map with an emotion curve. In the stage skin a process plays as a BPMN token: it splits at parallel gateways, waits at the join and follows the yes branch.
  • Data models, sequences and roadmaps. kind: er draws tables with typed, keyed rows and crow's foot relationships that meet the rows they join, and orrery import sql starts one from your CREATE TABLE statements. kind: sequence draws a call flow message by message, with replies dashed, activation bars and loop or alt fragments, played in order. kind: timeline draws a roadmap by month, quarter or year: lanes, status-styled bars, milestones, dependency arrows and a today marker.
  • Automatic layout you can steer. The Eclipse Layout Kernel places nested boundaries, routes edges at right angles, joins fan-in and fan-out into trunks and keeps the order you wrote unless that would cross edges. No coordinates to write; when you want a say, rank: first, align: , cols: 2 on a group and layout: { aspect: 4:3 } pin a node's place in the flow, line nodes up, grid a group's children and keep a figure compact enough to read in a README.
  • One spec, many figures. views: draws an overview and its details from one source (render --view all), so they cannot drift apart; classes: share presets, include: pulls in a frame every figure shares, and tags: color and restyle what they mark, with a legend row each.
  • Diagrams that stay true to the code. orrery import starts a spec from Terraform, CloudFormation or CDK output, Docker Compose, Kubernetes manifests or Mermaid, with every node's evidence: (the file, line and identifier it came from). orrery verify fails when a piece of evidence no longer exists, and --link makes each node a commit-pinned link to its code. orrery diff shows what changed between two versions as a colored picture, and the GitHub Action posts it, with the review, on every pull request.
  • Diagrams that move. Animated SVG by default: packets travel every edge at one speed, the main path plays as a story, line styles stay as drawn. animate: flow for marching dashes, --static for a still file.
  • Two skins, one layout. The default stage skin draws every diagram as an animated scene, dark by default: a hairline grid with one tint, ink tiles with each icon in a muted share of its own vendor color, mono caps labels, dim wires and one story that plays along them. skin: classic (or --skin classic) follows each vendor's own diagram style instead, for docs that must match the AWS, Azure or Google Cloud deck. Every position stays the same; dark and light.
  • Eight outputs from one spec. SVG for READMEs and docs, PNG for slides and chat (3x by default, sharp when zoomed), .drawio you can keep editing, .drawio.svg (one file that shows as an image anywhere and opens as an editable diagram in draw.io), a TSX component for React sites, a standalone HTML viewer with dark mode, pan and pinch zoom, Mermaid text for wikis that draw only Mermaid, and a sequence diagram of the main path. Every SVG and PNG carries its own spec, so orrery import picture turns a picture back into an editable diagram. orrery doc puts the figures into a design document as HTML, Markdown or Word.
  • Made for agents. A skill with a fast path and authoring rules, a JSON Schema, 482 short aliases (aws:s3, azure:aks, k8s:deploy, and business names such as generic:invoice and generic:approval), ranked icon search, a validator whose every finding names the subject and the fix, an MCP server for clients without skills, and agents that plan a diagram from your code and check it against it.
  • No install. The CLI, layout engine, PNG renderer, fonts and the official cloud packs ship in the skill folder (9 MB). Logo and glyph sets are not copied in: they load from their own npm libraries the first time a diagram uses them, verified by checksum and cached. Node.js 22 or newer is all it needs.

How it works

Install

Claude Code plugin:

/plugin marketplace add Sagargupta16/orrery

/plugin install orrery@orrery

Any agent that reads Agent Skills (Codex, Cursor, Gemini CLI, Kiro and others):

npx skills add Sagargupta16/orrery

gh skill install Sagargupta16/orrery orrery # GitHub CLI, any supported agent gemini extensions install https://github.com/Sagargupta16/orrery # Gemini CLI extension

Only the CLI, from npm:

npx @sagargupta1610/orrery doctor

npx @sagargupta1610/orrery render diagram.yaml -f all --theme both

Or from a clone: node orrery/skills/orrery/scripts/orrery.mjs doctor.

As an MCP server, for any client that speaks the Model Context Protocol (tools: authoring guide, validate, render, review, icon search, templates, patch candidates, draw.io link):

{ "mcpServers": { "orrery": { "command": "npx", "args": ["-y", "@sagargupta1610/orrery", "mcp"] } } }

That block goes in .mcp.json for Claude Code, ~/.gemini/settings.json for Gemini CLI, .cursor/mcp.json for Cursor and .kiro/settings/mcp.json for Kiro; Codex takes [mcp_servers.orrery] with command = "npx" and args = ["-y", "@sagargupta1610/orrery", "mcp"] in ~/.codex/config.toml. orrery mcp install writes that entry for you (claude-code, claude-desktop, cursor, vscode, gemini, codex or kiro, in the project or with user for every project), keeping every other server in the file. Each release publishes the server to the MCP Registry as io.github.Sagargupta16/orrery and attaches an .mcpb bundle for one-click install in Claude Desktop. In hosts that support MCP Apps, a rendered diagram opens in an inline viewer. orrery mcp --port 8765 serves the same tools over HTTP on 127.0.0.1, where specs are passed as text and nothing is read from or written to disk.

Quick start

Ask your agent for a diagram ("draw the architecture of this repo", "a three-tier web app on AWS across two Availability Zones", "turn this Mermaid flowchart into a Google Cloud diagram"). It writes a spec, validates it, renders it and checks the picture. Or write one yourself:

title: Orders API

direction: right groups: cloud: { type: aws:cloud } region: { type: aws:region, label: eu-west-1, in: cloud } nodes: users: { icon: aws:users, label: Customers } api: { icon: aws:api-gateway, in: region } fn: { icon: aws:lambda, label: Create order, in: region } table: { icon: aws:dynamodb, label: Orders, in: region } edges:

  • users -> api: HTTPS
  • api -> fn -> table
node skills/orrery/scripts/orrery.mjs render orders.yaml -f svg,png

Labels default to the official service names, so { icon: aws:lambda } reads "AWS Lambda". Edges use arrows: -> solid, --> dashed, ..> dotted, ==> thick, <-> both ways, a -> b, c to fan out. The full format is in spec.md.

Examples

aws-three-tier: a VPC across two Availability Zones with public, web and data subnets and an Auto Scaling group drawn across both zones, in the AWS deck's own group styles.

That is one of 77 reference diagrams across AWS (from agents on Bedrock AgentCore to disaster recovery, threat detection, network inspection, migration and contact centers), Azure, Google Cloud, IBM Cloud, Kubernetes, AI and ML, data platforms, CI/CD, C4, system design and business flows (flowcharts, a BPMN process, swimlanes, a state machine, an org chart, a mind map and a customer journey), each rendered from a spec in skills/orrery/examples and checked against the renderer by CI. Browse them all in light and dark, with each spec and every output to download, at [sagargupta.online/orrery/gallery](https://sagargupta.online/orrery/gallery/), or in examples/README.md with the command that renders each one. orrery init copies any of them as a starting point.

Validation that tells you the fix

$ orrery validate orders.yaml

error DG101 node "fn" uses unknown icon "aws:lamda" {"node":"fn","icon":"aws:lamda"} fix: use icon "aws:lambda" fix: run orrery icons search lamda error DG108 unknown key "lable" in node "db" {"where":"node \"db\"","key":"lable"} fix: rename "lable" to "label" failed: 2 error(s), 0 warning(s)

Spec errors (DG1xx) stop the render; composition warnings (DG2xx: an edge through a node, colliding labels, a diagram too wide to read) keep it going unless --strict is set. render --json writes every file atomically and prints a receipt with the size and SHA-256 of each output.

A review board that measures before it judges

orrery review looks at the diag

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx