GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者による説明(英語の原文)
Architecture diagrams with official AWS, Azure, GCP and Kubernetes icons, to SVG, PNG and draw.io
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
リンク先は作者自身のファイルです。私たちが置いたり再パッケージしたりしたものではありません。ファイルを開くと、Claude Desktopがインストールします。
ターミナルでこれを実行します
claude mcp add orrery -- npx -y @sagargupta1610/orrery mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"orrery": {
"command": "npx",
"args": [
"-y",
"@sagargupta1610/orrery",
"mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"orrery": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sagargupta1610/orrery",
"mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月8日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント Sagargupta16 で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.12.2)がレジストリに届いたのは6 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.js, MCPBも必要です。
同じカテゴリには:GitHub, Desktop Commander, Cloudflare MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
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.
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.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.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.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.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.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.animate: flow for marching dashes, --static for a still file.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..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.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.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.
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:
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.
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.
$ 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.
orrery review looks at the diag
冒頭だけを表示しています。続きはリポジトリで読めます