Ext Ops Panel
Open dashboard
Comparison

testdino vs agent-device

testdino is a plugin bundle for AI coding tools published by TestDino. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). agent-device is an MCP server published by callstack. 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
Marketplacetestdinoagent-device
Claude Code: claude-plugins-community Listed
Version: 1.0.0
Forks (GitHub): 331
Stars (GitHub): 4 637
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.21.27
Downloads/month (npm): 979 627
Downloads/week (npm): 291 005
Forks (GitHub): 333
Stars (GitHub): 4 996
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

testdino vs agent-device
Facttestdinoagent-device
Marketplaces that list it11
Stars (GitHub) (differs)4 637 (worse)4 996 (better)
Forks (GitHub) (differs)331 (worse)333 (better)
Last release (differs)Not published2026-10-12
Where it runs (differs)Remote server (mcp.testdino.com)On your machine (agent-device)
Transport (differs)Streamable HTTPstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)8Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/anthropics/claude-plugins-communitygithub.com/callstack/agent-device
Changes in the last 7 days (differs)02
First seen (differs)2026-10-122026-10-11
Endpoint at the last check (differs)Responded less than an hour agono remote endpoint we check

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

testdino

In its own words, on Claude Code: claude-plugins-community:

Use TestDino inside Claude Code through the hosted remote MCP server to inspect test runs, debug failing test cases, manage manual tests, and run TestDino audits.

agent-device

In its own words, on Official MCP Registry:

MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps

How to run each

testdino As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install testdino@claude-community

agent-device As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio agent-device -- npx -y agent-device mcp

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

Only testdino 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

Neither one's marketplaces publish the settings it asks for.

What it can do: testdino · What it can do: agent-device · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-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