Ext Ops Panel
Open dashboard
Comparison

AWS Labs Nova Canvas vs dev.rostro/rostro

AWS Labs Nova Canvas is an MCP server published by awslabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). dev.rostro/rostro is an MCP server published by rostro.dev. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-14. 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

Where each is published
MarketplaceAWS Labs Nova Canvasdev.rostro/rostro
Docker MCP Catalog Listed
Version: sha256:5582496accaa
Forks (GitHub): 1 805
Pulls (Docker Hub): 11 097
Stars (Docker Hub): 0
Stars (GitHub): 9 776
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.0.0
Forks (GitHub): 0
Stars (GitHub): 0
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 dev.rostro/rostro
FactAWS Labs Nova Canvasdev.rostro/rostro
Marketplaces that list it11
Stars (GitHub) (differs)9 776 (better)0 (worse)
Pulls (Docker Hub) (differs)11 097No figure on Docker Hub
Forks (GitHub) (differs)1 805 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)On your machine (mcp/nova-canvas-mcp-server)Remote server (proto.rostro.dev/mcp)
Transport (differs)stdioStreamable HTTP
Tools it declares (differs)2Not published
Environment variables it asks for (differs)5, secrets among them: 2Not published
Licence (differs)Apache-2.0Not stated
Repository (differs)github.com/awslabs/mcpgithub.com/francis-ros/rostro-mcp-server
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkAnswered with HTTP 307 (39 h ago)

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

In its own words, on Docker MCP Catalog:

AI image generation using Amazon Nova Canvas.

dev.rostro/rostro

In its own words, on Official MCP Registry:

Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.

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)

dev.rostro/rostro As a remote MCP server

Claude Code
claude mcp add --transport http rostro https://proto.rostro.dev/mcp

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

Only dev.rostro/rostro has a remote endpoint we check. How we check endpoints

Tools each declares

The marketplaces of dev.rostro/rostro publish no list of tools, so we do not compare tools.

Settings each asks for

The marketplaces of dev.rostro/rostro publish no settings it asks for, so we do not compare settings.

What it can do: AWS Labs Nova Canvas · What it can do: dev.rostro/rostro · Compare two other plugins

Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. 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