Openflowkit Mcp

io.github.openflowkit由 GitHub 帳號 openflowkit 發布v0.3.0更新於 Nov 7, 2026

Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.

已驗證STDIO僅桌面開發者工具媒體與設計

概覽

AI 產生的概覽

讓助理在 OpenFlowKit 即時畫布或圖表檔案上繪製、編輯、改樣式並匯出架構圖,還能將程式碼庫映射成圖。

可以做什麼
  • 用文字或 Mermaid 建立與更新圖表、加入形狀,並改樣式、移動或刪除元素
  • 讀取文件、頁面、圖表文字與目前選取的內容
  • 擷取結果截圖,並匯出 SVG、PNG、PDF、JSON 或動畫 SVG
  • 開啟、儲存與驗證圖表檔案,列出節點類型與起始範本
  • 分析程式碼儲存庫以找出架構、產生漂移報告並解釋元素
適用情境
適合讓助理把描述、README 中的 Mermaid 或現有程式碼儲存庫變成可編輯的架構圖,或讓提交到儲存庫的圖表與程式碼保持同步。
執行需求
透過 npx 以 stdio 在本機執行,需要 Node 20.11 以上版本。若要在即時畫布上繪製,需開啟 OpenFlowKit 應用程式並透過 Connect agent 面板連線,該面板會提供配對權杖。未開啟應用程式時,工具會作用於儲存庫中的 .openflow.json 檔案。
安裝前請注意
助理會修改畫布上的圖表並編輯儲存庫中的圖表檔案;每次變更算一步復原,但仍會寫入資料。連線即時畫布會使用應用程式提供的配對權杖。儲存庫映射會從 GitHub 讀取程式碼,私有儲存庫需要唯讀 GitHub 權杖。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Openflowkit Mcp,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

[OpenFlowKit logo]

OpenFlowKit

Architecture diagrams you draw, write as code, or hand to your agent.
Free, open source and local-first. Paste a GitHub repo and get its map, every arrow cited to a line of code.

Open the app  ·  Docs  ·  MCP setup  ·  Discussions  ·  Issues

[CI status] [MIT license] [MCP server version on npm] [CLI version on npm]

[OpenFlowKit: #4 Product of the Week in Design Tools on Product Hunt]

[An agent draws an architecture diagram on the OpenFlowKit canvas, live; the user drags a box, edits one line of text and regenerates]

Why OpenFlowKit

1. Your agent draws on your canvas, live

Connect Claude Code, Cursor or any MCP client and ask for a diagram. The agent reads the page, draws, restyles and takes a screenshot to check its own work while you watch. Every change it makes is one undo step, like your own. Connect your agent ↓

2. Text and canvas are the same diagram

flowchart right  Client [blue] -> "API Gateway" [emerald] : HTTPS  "API Gateway" -> Queue [queue, amber]  Queue -> Worker  Worker -> Store [cylinder, red, bold]

Open the code panel (⌥C), paste this into it and press ⌘↵. Drag things around on the canvas or edit the text; ⌘↵ regenerates the frame from the text as one undo step. Paste Mermaid, Structurizr or D2 and it converts.

[The code panel beside the canvas: the same diagram as text and as shapes]

3. Paste a GitHub repo, get its map

Type owner/repo into the box on an empty canvas and press Map repo, or open app.openflowkit.com/#/map/github/<owner>/<repo> (try a sample). Your browser reads the repo from GitHub and draws its parts. Boxes open in place, and every arrow lists the file:line behind it, linked to the code. No key and no install. For a private repo, add a read-only GitHub token on the page, or map a checkout: npx openflowkit map . --html map.html (private repos).

[The map of GoogleCloudPlatform/microservices-demo: a click on checkoutservice opens it in place, showing the files inside, while the side panel lists what it talks to]

4. Export it, including the animation

PNG, SVG, PDF, JSON, or Copy as Mermaid for a README. Add an animate block to the text above to name the steps, and the export renders animated SVG, GIF, MP4 or WebM in your browser.

animate build 6s loop {  step Client  step Client -> "API Gateway" : HTTPS  step Queue, Worker  step Store hold 2s}

[The diagram above building step by step, exported as an animated SVG]

That animation is the two snippets above, exported by the app as an animated SVG. GitHub plays it like an image.

Ten diagram types, one language

Every type is the same short, forgiving text, with per-line errors that say how to fix them. Each picture below is the first example on its docs page, rendered by the openflowkit CLI.

[Architecture diagram with Node.js and AWS Lambda icons]
Architecture · cloud icons, groups, a C4 model with views
[Sequence diagram of a login]
Sequence · alt / opt / loop, notes, activations
[Flowchart]
Flowchart · shapes, decisions, groups
[Entity-relationship diagram]
ERD · columns, keys, crow's-foot cardinality
[State machine]
State · start and end, composite states
[Class diagram]
Class · members, stereotypes, relations
[Mind map]
Mind map · indentation is the tree
[Git graph]
Git graph · branches, merges, tags
[Bar chart]
Chart · data written as text, editable in a table
[Phone wireframe]
Wireframe · 35 controls on phone, tablet or desktop screens

The language is versioned and written down in one file: src/dsl/grammar.md (docs). The same text powers the code panel, the assistant, the MCP tools and the CLI.

Quick start

In the browser: app.openflowkit.com. Nothing to install, no account.

In a terminal: npx openflowkit (Node 20.11+).

Run it locally (Node 22.22+):

bash
git clone https://github.com/openflowkit/openflowkit.gitcd openflowkitnpm install && npm run dev      # http://localhost:3000

Connect your agent

OpenFlowKit has one set of agent tools. Pick the row for where your agent runs:

Your agent runs…How to connectWhat it can do
On your computer: Claude Code, Cursor, VS Code, Claude Desktop, WindsurfThe MCP server, belowEverything: draws on your open canvas (one undo step per change), edits .openflow.json files in your repo, maps a codebase, takes screenshots
In a chat app: claude.ai, Claude Desktop, ChatGPTAdd a custom connector: https://mcp.openflowkit.com/mcp, choose No sign-inDraws a diagram in the chat as a card, with Open in OpenFlowKit. Not on your open canvas
In your browser (experimental)Nothing to install: open a diagram in a browser whose agent supports WebMCPReads and edits the diagram you have open

[Add OpenFlowKit to Cursor] [Install OpenFlowKit in VS Code]

For Claude Code, one line:

bash
claude mcp add -s user openflowkit -- npx -y openflowkit mcp

For Codex: codex mcp add openflowkit -- npx -y openflowkit mcp.

For Claude Desktop, Windsurf and any other MCP client:

json
{  "mcpServers": {    "openflowkit": { "command": "npx", "args": ["-y", "openflowkit", "mcp"] }  }}

Restart the agent, then click Connect agent in the app, or open app.openflowkit.com/#/connect. That panel has the steps for each client and copies the same config with a pairing token. With no app open, the same tools edit .openflow.json files in your repo. Every client, step by step, with fixes: Connect your agent.

Plugins: Claude Code and Codex (server and skill in one install)
bash
# Claude Codeclaude plugin marketplace add openflowkit/openflowkitclaude plugin install openflowkit@openflowkit
# Codex: add the marketplace, then install OpenFlowKit from the Plugins Directorycodex plugin marketplace add openflowkit/openflowkit

The skill (skills/openflowkit/SKILL.md) tells an agent when a diagram helps, how to write it, and to save it beside the code. Agents that read the web get the same text at https://app.openflowkit.com/llms.txt.

Working with agents

The MCP server gives your agent the operations you have, on the live canvas or on files.

It canWith
Draw a diagram from text or Mermaid, then change itcreate_diagram, update_diagram, add_shape
Read every page, the text behind a diagram, and what you selectedget_document, get_diagram, list_pages
Restyle and move what is already therestyle, move, delete
See its own resultscreenshot returns a real image the model can look at
Hand you filesexport: SVG, PNG, PDF, JSON or an animated SVG
Read your repodiscover_architecture, drift_report, explain_element

Things to ask for:

  • "Draw the architecture of this repository."
  • "Make the boxes I selected red and add a cache in front of the API."
  • "Turn the Mermaid in our README into a diagram I can edit."
  • "Compare architecture.ofk with the code and tell me what drifted."

Your canvas edits are safe: if you moved, restyled or renamed something and the agent regenerates from text, get_diagram hands it the text that keeps each edit, and update_diagram reports anything it had to drop. Every agent change is one undo step, and the Connect panel shows the last one with an Undo button.

All 29 tools

Sixteen editor operations, which also work on files: create_diagram, update_diagram, get_diagram, list_diagrams, get_syntax, search_icons, find_icons_for, move, style, delete, add_shape, export, screenshot, fit_view, get_document, list_pages.

Thirteen for files and repositories: openflow_create, openflow_open, openflow_save, whoami, server_info, validate_openflow_dsl, list_diagram_node_types, list_starter_templates, get_starter_template, analyze_codebase, discover_architecture, drift_report, explain_element.

Arguments and examples: MCP server docs. The op manifest is src/agent/manifest.ts. Requires Node 20.11+.

Bring your own key instead: ⌘J opens the assistant. Pick Claude, OpenAI, Gemini, Groq, Mistral, Cerebras, NVIDIA, OpenRouter, Ollama or any OpenAI-compatible endpoint (LM Studio…) and paste a key. The key stays in this browser, and the reply arrives as a proposal you apply or dismiss.

Bring the diagrams you already have

Paste into the code panel and it converts, with an honest list of anything it couldn't carry. Mermaid pasted straight onto the canvas draws in place.

FromWhat converts
Mermaidflowchart / graph, sequenceDiagram, stateDiagram, erDiagram, classDiagram, mindmap, architecture, gitGraph
Structurizr DSLthe model, views and styles, as a C4 workspace with one page per view
D2shapes, connections and containers

Going back out, Copy as Mermaid writes a flowchart or sequence diagram as Mermaid text for a README or wiki. Mermaid · coming from Structurizr

In your repo and CI

The openflowkit CLI runs the same engine as the app, from any terminal or CI job:

bash
npx openflowkit render diagram.ofk -o diagram.svg   # Mermaid, D2, Structurizr or DSL → SVGnpx openflowkit validate diagram.ofk --strict       # exit 1 on an errornpx openflowkit convert flow.mmd -o flow.openflow.jsonnpx openflowkit discover . --out architecture.ofk   # draft a C4 model of this reponpx openflowkit drift .                             # exit 1 when the code moved on

[Running npx openflowkit: a welcome box, OPEN FLOWKIT in orange block letters, and three commands to try]

Commit architecture.ofk next to the code and drift keeps it honest in CI. The PR diagrams Action comments on a pull request with how its diagrams changed: node and connector counts, the text diff, and drift for .ofk models. CLI · GitHub Action

Exports and sharing

FormatNotes
PNG1× or 2×; light, dark or print theme; transparent background optional
SVG, PDFvector, with icons and the Inter font embedded
JSONthe whole document, every page; opens in any browser
Animated SVG, GIF, MP4, WebMmade in your browser from the animate block or the connector order
Copy as Mermaidflowchart and sequence
Share linksa view-only link, encrypted in your browser; or an editable copy, the code inside the link, nothing uploaded

Keyboard

Every action has a key, and ? lists them all in the app.

The ones you'll use first
KeyAction
V R O T Aselect, rectangle, ellipse, text, connector
⌥C · ⌘↵code panel · generate from text
⌘JAI assistant
Mswitch Canvas and Map
⌘Ffind on the canvas
⇧1 · ⇧2fit everything · zoom to selection
⌘G · ⌘Dgroup · duplicate
Enteredit the selected shape's label

On Windows and Linux, Ctrl and Alt replace ⌘ and ⌥.

How it works

[You, your agent and imported Mermaid, Structurizr or D2 all become OpenFlow DSL; the compiler turns it into one undo step on the scene document, which feeds the canvas, the exports and browser storage]

This diagram is OpenFlowKit text too: how-it-works.ofk, exported as an animated SVG with the pulse preset.

You and your agent can also draw straight on the canvas; every edit, from text or by hand, is a command on the same document.

Any frame on the canvas writes back out as canonical text, and format(format(x)) == format(x) holds in the tests. The language and document code is plain TypeScript with no React, Pixi or DOM, which is why the same compiler runs in the browser, the MCP server and the CLI. The full tour: ARCHITECTURE.md.

Repository layout
PathWhat
src/dsl/the language: grammar, parser, diagram families, compile and serialize, repo discovery
src/opencanvas/the editor: document model and commands, Pixi renderer, exporters, React UI
src/agent/the operations agents call, the bridge protocol, the op manifest
mcp-server/the published MCP server and openflowkit CLI
cli/openflowkit on npm: the short name for the CLI
plugin/, skills/the Claude Code and Codex plugins, and the agent skill
action/the PR diagrams GitHub Action
worker/the share-link Worker (stores ciphertext only)
stats/the private usage dashboard Worker
docs-site/the docs site

Self-host

bash
docker build -t openflowkit . && docker run --rm -p 3045:3045 openflowkit   # http://localhost:3045

The image is the static build behind nginx, with the same headers as the hosted app. Content security policy, AI providers on your own network, and share links: self-hosting.

Privacy

Your diagrams stay in your browser. Something leaves it only when you choose: AI with your own key goes to that provider, a share link uploads an encrypted copy, a repo map reads from GitHub. No account needed. We collect basic usage stats to improve OpenFlowKit; turn them off in Settings. Back up everything at once with Download all diagrams on Home; Import restores it in any browser.

FAQ

Is it free? Yes: MIT licensed, free to use and to self-host. A Pro plan for teams is planned; the waitlist is in the app.

Does it work offline? Once the page is open, drawing, the code panel and exports run in the page. AI, share links and repo maps need the network. For no internet at all, self-host it.

Which browsers? A current desktop browser with WebGL. The automated tests run in Chromium.

Can my team edit together? Not in real time. A view-only link is a snapshot, an editable link hands each person their own copy, and .openflow.json and .ofk files live happily in git.

More: FAQ.

Contributing

Issues, ideas and PRs are welcome. Start with CONTRIBUTING.md for setup and the checks, and ARCHITECTURE.md for how the code fits together. Questions go to Discussions. What changed in each version: CHANGELOG.md.

Report security issues privately, as SECURITY.md describes. MIT licensed, see LICENSE.

[Contributors]


[OpenFlowKit logo]

If OpenFlowKit saved you a diagram, give it a ⭐ on GitHub.
It's how other people find it.

Open the app  ·  Docs  ·  Contribute  ·  Discussions  ·  Report a bug

來源:README.md,提交 9786bc7

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

3
  1. v0.3.0最新Nov 7, 2026
  2. v0.2.4Oct 13, 2026
  3. v0.2.3Oct 12, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分