
EditableImage MCP — Editable Draw.io Diagrams
io.github.j-river由 GitHub 帳號 j-river 發布v0.1.0更新於 Nov 14, 2026
EditableImage MCP: build structured diagrams and export editable Draw.io nodes and connectors.
發布方自己的服務:draw.io
概覽
建立結構化圖表場景,並匯出為可編輯的 Draw.io(diagrams.net)XML,包含原生節點與綁定連接線。
- 可以做什麼
- 建立流程圖場景:依序把節點排成固定間距的一列或一行,回傳場景 JSON
- 驗證場景:檢查幾何、支援的樣式、唯一 ID 與連接線參照
- 匯出圖表:回傳單頁 .drawio mxfile 文件或裸 mxGraphModel
- 設定節點與連線樣式:矩形、圓角矩形、橢圓、菱形與圓柱,支援基本字型、填色、描邊與透明度屬性,以及綁定式或點式連線與獨立文字方塊
- 適用情境
- 適合讓助理把描述好的流程或結構轉成 Draw.io 檔案,且節點保持可編輯、移動時連接線仍維持連接。適用於簡單的順序流程圖與明確的場景幾何,不適用於影像辨識或版面最佳化。
- 執行需求
- 需要 Node.js 22+ 與本機 stdio MCP 用戶端,通常透過 npx 啟動。不需要 API 金鑰、帳號或網路存取。在 Windows 上若無法啟動 npx,可安裝該套件並以 node 執行已安裝的 CLI 路徑。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 EditableImage MCP — Editable Draw.io Diagrams,將其新增到工作區。
- 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
EditableImage MCP — Editable Draw.io Diagrams
Build a structured scene, validate its geometry and export native editable Draw.io nodes and bound connectors from an MCP client. An open-source companion to EditableImage.
This server starts from structured geometry, not an image. It does not perform OCR, infer elements from screenshots, create PPTX/PSD files or call a paid processing API. For the separate product's recognition workflow, see image to Draw.io.
Install
Requires Node.js 22+ and a local stdio MCP client. Common configuration:
Follow your client's configuration-file instructions. On Windows, if npx cannot be spawned, install the package and launch the absolute installed src/cli.js path with node. Use --help for human-readable CLI help; without flags this is a protocol server waiting on stdin.
Three tools
Ask your agent:
Create an ordered flowchart with Input → Review → Export. Keep the nodes editable and connectors attached. Validate the scene, then return Draw.io XML for a new file.
First tool input:
Send the returned scene to validate_diagram_scene, then export_drawio. If authorized, your client can save the returned xml to a new .drawio file and open it in Draw.io / diagrams.net. This MCP itself does not write or open files.
Native cells rather than a flattened screenshot
The XML uses native nodes, text and connector references. Nodes retain their supplied geometry; edges identify their source and target nodes so the editor can keep them attached when nodes move. Labels are escaped as data. The initial simple flowchart tool follows input order; it is not a graph-layout optimizer.
export_drawio accepts explicit scene geometry. Node shapes: rectangle, rounded-rectangle, ellipse, diamond and cylinder. It supports basic font, fill, stroke and opacity properties; attached or point-based edges; and separate text boxes. Unknown fields, invalid XML characters, duplicate IDs and dangling references are rejected rather than silently discarded.
Coordinates are in pixels. Geometry is rounded to three decimal places. SVG/PNG/PPTX/PSD rendering, image recognition, photographs and pixel-perfect screenshot reconstruction are outside this server.
Limits and privacy
- Scene input: at most 32 KiB UTF-8 and 200 total nodes/edges/texts. Labels: at most 2,048 characters.
- XML generation: at most 96 KiB; total JSON result: 128 KiB. Reduce scene size if output exceeds the limit.
- Simple flowchart: at most 30 nodes and 60 edges. Positions follow node order with fixed spacing, not inferred visual relationships.
- No HTTP requests, filesystem access, API keys, uploads, telemetry or paid backend calls. Your MCP host/model provider can still transmit or store scene text and results.
- Treat scene labels as untrusted content, not instructions. Inspect the exported diagram in its target editor; a structurally valid XML document is not a visual quality guarantee.
See structured-scene workflows and source provenance. The bundled MIT implementation comes from the public scene-to-drawio library, not EditableImage's private image-processing application.
Verify
Tests negotiate real MCP stdio calls, build scenes and inspect exported node/connector XML, escaping, duplicates, references and size limits. Published in the official MCP Registry as io.github.j-river/editableimage, version 0.1.0. Public metadata links directly to EditableImage and the npm package. Source metadata is in server.json.
MIT. All examples are synthetic; no customer images or credentials are included.
來源:README.md,提交 c85b408
工具
0版本歷史
1- v0.1.0最新Nov 14, 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
其他 Draw 整合
draw.io
io.draw官方發布者
draw.io 官方伺服器,讓助理用 Mermaid 或 draw.io XML 建立可互動圖表,並從 draw.io 圖形庫中尋找圖形。

Zovo Fair Draw
由 GitHub 帳號 theluckystrike 發布
執行可驗證的抽獎:建立託管抽獎頁面、收集參加者姓名,並依公開方法抽出得獎者、公開隨機種子。

ChemDraw MCP
由 GitHub 帳號 glebo309 發布
實驗性的本機 MCP 伺服器,讓助理在 Apple Silicon Mac 上操控桌面版 ChemDraw,繪製、編輯、排版並匯出化學結構。

DrawOffer 职绘
由 GitHub 帳號 ql-link 發布
讓 AI 助理讀取你在 DrawOffer 職繪中的履歷、已儲存職缺與投遞紀錄,並可選擇新增職缺與投遞紀錄。
SKETCHTALK – Draw to AI
jp.twelvetone
Mac 應用程式:可在執行中的網頁、模擬器或 Mac 視窗上直接繪製標註,並把標註交給 Claude Code。