Ext Ops Panel
Open dashboard
Comparison

AWS Labs Nova Canvas vs Open Design

Open Design is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑16.

AWS Labs Nova Canvas is an MCP server published by awslabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). Open Design is a plugin bundle for AI coding tools published by feimacode. No marketplace we read lists it any more. As of our marketplace pass on 2026-10-18. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceAWS Labs Nova CanvasOpen Design
Docker MCP Catalog Listed
Version: sha256:5582496accaa
Forks (GitHub): 1 815
Pulls (Docker Hub): 11 144
Stars (Docker Hub): 0
Stars (GitHub): 9 788
Not marked · First seen
Not listed
Community marketplace feimacode/open-design-agent-kit Not listed Removed on 2026-10-16
Version: 0.1.0
Forks (GitHub): 0
Stars (GitHub): 2
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

AWS Labs Nova Canvas vs Open Design
FactAWS Labs Nova CanvasOpen Designno longer listed ·
Marketplaces that list it (differs)10
Stars (GitHub) (differs)9 7882
Pulls (Docker Hub) (differs)11 144No figure on Docker Hub
Forks (GitHub) (differs)1 8150
Last releaseNot publishedNot published
Where it runs (differs)On your machine (mcp/nova-canvas-mcp-server)Installs as a plugin bundle
Transport (differs)stdioNot stated
Tools it declares (differs)2Not published
Environment variables it asks for (differs)5, secrets among them: 21, secrets among them: 1
Parts of the bundle (differs)Not a bundle38
Licence (differs)Apache-2.0MIT
Repository (differs)github.com/awslabs/mcpgithub.com/feimacode/open-design-agent-kit
Changes in the last 7 days (differs)04
First seen (differs)2026-10-112026-10-13

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of Open Design

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • Superdesign

    Design or redesign frontend UI and marketing graphics on the Superdesign infinite canvas. Reads your codebase for context, sets up a design system, and generates branchable design…

    by superdesigndev · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Community GitHub marketplaces · Describes nearly the same job

  • get-design-done

    Agent-orchestrated design pipeline for Claude Code. Five stages (brief → discover → plan → design → verify), 33 specialized agents, 12 tool connections including Figma, shadcn/ui…

    by hegemonart · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

  • design-with-claude

    29 specialized design agents as Claude Code commands. Bring expert design knowledge into every coding session - accessibility, motion design, design systems, color theory…

    by imsaif · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

  • Figma

    Figma workflows for design implementation, Code Connect templates, and design system rule generation.

    by Figma · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes nearly the same job

  • Product Design

    The Product Design plugin is built for turning early ideas into prototypes teams can review. It starts design and build work by confirming the brief, then helps teams explore…

    by OpenAI · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes nearly the same job

  • Design

    Accelerate design workflows — critique, design system management, UX writing, accessibility audits, research synthesis, and dev handoff. From exploration to pixel-perfect specs.

    by Anthropic · Plugin bundle

    Listed on: Claude: knowledge-work-plugins · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

AWS Labs Nova Canvas

In its own words, on Docker MCP Catalog:

AI image generation using Amazon Nova Canvas.

Open Design

In its own words, on Community GitHub marketplaces:

Generate design artifacts (landing pages, decks, prototypes, dashboards) using Open Design's bundled skills and design systems, directly in your project.

How to run each

AWS Labs Nova Canvas As a local MCP server: Docker image

Claude Code
claude mcp add --env "AWS_SECRET_ACCESS_KEY=<YOUR_AWS_SECRET_ACCESS_KEY>" --env "AWS_SESSION_TOKEN=<YOUR_AWS_SESSION_TOKEN>" --transport stdio awslabs-nova-canvas -- docker run -i --rm -e AWS_SECRET_ACCESS_KEY -e AWS_SESSION_TOKEN mcp/nova-canvas-mcp-server

Requires: AWS_SECRET_ACCESS_KEY (secret), AWS_SESSION_TOKEN (secret)

Open Design

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

The marketplaces of Open Design publish no list of tools, so we do not compare tools.

Settings each asks for

Only AWS Labs Nova Canvas asks for

  • AWS_ACCESS_KEY_ID
  • AWS_PROFILE
  • AWS_REGION
  • AWS_SECRET_ACCESS_KEY (secret)
  • AWS_SESSION_TOKEN (secret)

Only Open Design asks for

  • OPEN_DESIGN_FIGMA_TOKEN (secret)

Settings as each marketplace publishes them. Asking for fewer is not better in itself.

What it can do: AWS Labs Nova Canvas · What it can do: Open Design · Compare two other plugins

Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built