AWS Labs Nova Canvas vs Banana Claude
AWS Labs Nova Canvas is an MCP server published by awslabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). Banana Claude is a plugin bundle for AI coding tools published by AgriciDaniel. Marketplaces we read that list it: 1 (Community GitHub marketplaces). As of our marketplace pass on 2026-10-27. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  AWS Labs Nova Canvas | |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:5582496accaa Forks (GitHub): 1 830 Pulls (Docker Hub): 11 434 Stars (Docker Hub): 0 Stars (GitHub): 9 835 Not marked · First seen |
Not listed |
| Community marketplace agricidaniel/banana-claude | Not listed | Listed Version: 3.1.0 Forks (GitHub): 256 Stars (GitHub): 1 138 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
| Fact | AWS Labs Nova Canvas | Banana Claude |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 9 835 (better) | 1 138 (worse) |
| Pulls (Docker Hub) (differs) | 11 434 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 1 830 (better) | 256 (worse) |
| Last release (differs) | Not published | 2026-10-21 |
| Where it runs (differs) | On your machine (mcp/nova-canvas-mcp-server) | Installs as a plugin bundle |
| Transport (differs) | stdio | Not stated |
| Tools it declares (differs) | 2 | Not published |
| Environment variables it asks for (differs) | 5, secrets among them: 2 | 2, secrets among them: 1 |
| Parts of the bundle (differs) | Not a bundle | 4 |
| Licence (differs) | Apache-2.0 | MIT |
| Repository (differs) | github.com/awslabs/mcp | github.com/agricidaniel/banana-claude |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-11 | 2026-10-15 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
AWS Labs Nova Canvas
AI image generation using Amazon Nova Canvas.
Banana Claude
Brief-led image generation, editing, review, and bounded multi-model orchestration with current Gemini image models. Requires Claude Code 2.1.199+, Python 3.11+ with python3 on PATH, and Linux, macOS, or WSL for generation.
How to run each
AWS Labs Nova Canvas As a local MCP server: Docker image
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-serverRequires: AWS_SECRET_ACCESS_KEY (secret), AWS_SESSION_TOKEN (secret)
Banana Claude As a Claude Code plugin
/plugin marketplace add agricidaniel/banana-claude
/plugin install banana-claude@banana-claude-marketplaceCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of Banana Claude 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_IDAWS_PROFILEAWS_REGIONAWS_SECRET_ACCESS_KEY (secret)AWS_SESSION_TOKEN (secret)
Only Banana Claude asks for
GEMINI_API_KEY (secret)PYTHONUNBUFFERED
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: Banana Claude · 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.