OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Draw.io Scientific Illustrator

Draw.io Scientific Illustrator is a Codex plugin that uses MCP servers to control the visible draw.io desktop canvas and edit its active graph model for step-by-step scientific illustration. It also includes utilities for validating saved .drawio files and exporting PNG, SVG, PDF or JPG deliverables.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Draw.io Scientific Illustrator — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it for a stepwise, reference-led scientific diagram workflow in Codex when the figure can be represented with editable draw.io primitives.

Who it is for

  • Researchers and technical illustrators who want to recreate scientific figures as editable draw.io diagrams.
  • Codex users who want an agent to make and refine diagram changes directly on the visible canvas.

Documented uses

  • Recreate a reference figure by decomposing it into editable shapes, labels, arrows and layout.
  • Review and refine figure sections while changes appear on the draw.io canvas.
  • Validate saved .drawio documents and export finished diagrams to image or PDF formats.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. Its README says this version no longer receives feature or compatibility updates; development has moved to scientific-illustrator.

  • Requires Codex desktop or CLI with plugin support and draw.io desktop installed locally.
  • Git is required for the documented manual installation; Node.js 22 or newer is recommended when MCP servers run outside Codex’s bundled runtime.
  • The live editing path uses draw.io’s graph API through a localhost-only MCP server rather than OS mouse or keyboard automation.
  • The legacy README identifies Windows as the tested platform, while describing common draw.io path detection on Windows, macOS and Linux.
  • Dense imagery and complex plots may exceed the live API’s emphasis on editable primitives.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the legacy plugin manually

Register the repository as a Codex marketplace and add its plugin.

Before you start

  • Codex desktop app or Codex CLI with plugin support
  • Git
  • draw.io desktop installed locally

Steps

  1. Clone the repository and change into its directory.

  2. Run codex plugin marketplace add "$(pwd)".

  3. Run codex plugin add drawio-scientific-illustrator@drawio-scientific-tools.

  4. Restart Codex and start a new task.

Expected outcome

The legacy plugin is added to Codex; restarting and starting a new task loads its skill and MCP tools.

Guide limitations

  • This repository no longer receives feature or compatibility updates; development has moved to scientific-illustrator.
  • Node.js 22 or newer is recommended if running the MCP servers outside the bundled Codex runtime.
Documentation 1 ↗
Source-based practical guide

Create a reference-based figure in Codex

Use the plugin workflow to recreate a supplied reference in the live draw.io canvas.

Before you start

  • The plugin installed in Codex
  • draw.io desktop installed locally
  • A PNG, JPEG, SVG or rendered PDF page to use as a reference

Steps

  1. Restart Codex after installation and create a new task.

  2. Attach the reference image or rendered PDF page.

  3. Mention Draw.io Scientific Illustrator or select the plugin in the composer.

  4. Specify desired pacing and output formats; the README’s example asks for stepwise drawing, visual review and refinement, then saving a .drawio file and exporting a PNG preview.

Expected outcome

The documented workflow has Codex build and review editable figure elements on the visible draw.io canvas, then save and export the requested deliverables.

Guide limitations

  • The README identifies Windows as the tested platform for this legacy version.
  • Dense microscopy images, photographs, heatmaps and complex plots may need image-insertion support beyond the live API.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
icebird1998/drawio-scientific-illustrator · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

scientific-illustrator — The repository README identifies this as the successor where ongoing development, releases and fixes have moved.