Ext Ops Panel
Open dashboard
Comparison

canvas-apps vs AgentMD

canvas-apps is a plugin bundle for AI coding tools published by microsoft. Marketplaces we read that list it: 1 (Copilot CLI: github/copilot-plugins). AgentMD is an MCP server published by djrobson5. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-16. 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
Marketplacecanvas-appsAgentMD
Copilot CLI: github/copilot-plugins Listed
Version: not stated
Forks (GitHub): 209
Stars (GitHub): 1 010
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.1.4
Downloads/month (npm): 574
Downloads/week (npm): 41
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

canvas-apps vs AgentMD
Factcanvas-appsAgentMD
Marketplaces that list it11
Stars (GitHub) (differs)1 010 (better)0 (worse)
Forks (GitHub) (differs)209 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleRemote server (www.getagentmd.com/api/mcp)
Transport (differs)Not statedStreamable HTTP
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published2, secrets among them: 1
Licence (differs)MITNot stated
Repository (differs)github.com/microsoft/power-platform-skillsgithub.com/djrobson5/agentmd-mcp
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkResponded 26 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

canvas-apps

In its own words, on Copilot CLI: github/copilot-plugins:

Build Power Apps Canvas Apps using the Canvas Authoring MCP server.

AgentMD

In its own words, on Official MCP Registry:

Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved

How to run each

canvas-apps

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

AgentMD As a remote MCP server

Claude Code
claude mcp add --transport http agentmd https://www.getagentmd.com/api/mcp --header "Authorization: Bearer <YOUR_TOKEN>"

Requires: AGENTMD_API_KEY (secret), Authorization header

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

Only AgentMD has a remote endpoint we check. How we check endpoints

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of canvas-apps publish no settings it asks for, so we do not compare settings.

What it can do: canvas-apps · What it can do: AgentMD · Compare two other plugins

Data comes from the public marketplace file https://github.com/github/copilot-plugins/blob/HEAD/.github/plugin/marketplace.json. 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