
EditableImage MCP — Editable Draw.io Diagrams
io.github.j-riverPublished by GitHub account j-riverv0.1.0Updated Nov 14, 2026
EditableImage MCP: build structured diagrams and export editable Draw.io nodes and connectors.
The publisher's own server: draw.io
Overview
Builds structured diagram scenes and exports them as editable Draw.io (diagrams.net) XML with native nodes and attached connectors.
- What you can do
- Create flowchart scenes: place ordered nodes in a fixed-spacing row or column and get scene JSON back
- Validate scenes: check geometry, supported styles, unique IDs and connector references
- Export diagrams: return a single-page .drawio mxfile document or a bare mxGraphModel
- Style nodes and edges: rectangles, rounded rectangles, ellipses, diamonds and cylinders, with basic font, fill, stroke and opacity properties, attached or point-based edges and separate text boxes
- When to use it
- Use it when you want an assistant to turn a described process or structure into a Draw.io file whose nodes stay editable and whose connectors stay attached when moved. It suits simple ordered flowcharts and explicit scene geometry, not image recognition or layout optimization.
- Requirements
- Node.js 22+ and a local stdio MCP client; typically launched with npx. No API keys, accounts or network access are needed. On Windows, if npx cannot be spawned, install the package and run the installed CLI path with node.
Installation
In SourceWeft
- Open EditableImage MCP — Editable Draw.io Diagrams in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
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.
Source: README.md at commit c85b408
Tools
0Version history
1- v0.1.0LatestNov 14, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Draw integrations
draw.io
io.drawOfficial publisher
Official draw.io server that lets an assistant create interactive diagrams from Mermaid or draw.io XML and look up shapes from draw.io's stencil libraries.

Zovo Fair Draw
Published by GitHub account theluckystrike
Runs verifiable prize draws: creates a hosted draw page, collects entrant names, and picks winners with a published method and revealed seed.

ChemDraw MCP
Published by GitHub account glebo309
Experimental local MCP server that lets an assistant drive desktop ChemDraw on Apple Silicon Macs to draw, edit, lay out and export chemical structures.

DrawOffer 职绘
Published by GitHub account ql-link
Lets an AI assistant read your DrawOffer job-search resumes, saved jobs and application records, and optionally save new jobs and applications.
SKETCHTALK – Draw to AI
jp.twelvetone
Mac app that lets you draw on a live web page, Simulator or Mac window and hand those marks to Claude Code.