Ext Ops Panel
Open dashboard
Comparison

zeabur vs Agent Lab Deploy

zeabur is a plugin bundle for AI coding tools published by zeabur. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Agent Lab Deploy is an MCP server published by jinhsueh. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-18. 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
MarketplacezeaburAgent Lab Deploy
Claude Code: claude-plugins-community Listed
Version: 1.21.3
Forks (GitHub): 11
Stars (GitHub): 39
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 2026.10.07
No figure published
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

zeabur vs Agent Lab Deploy
FactzeaburAgent Lab Deploy
Marketplaces that list it11
Stars (GitHub) (differs)39No figure on GitHub
Forks (GitHub) (differs)11No figure on GitHub
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleRemote server (mcp.agentlab.cresclab.com/mcp)
Transport (differs)Not statedStreamable HTTP
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)32Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/zeabur/zeabur-claude-plugingithub.com/chatbotgang/franky
Changes in the last 7 days00
First seen (differs)2026-10-122026-10-11
Endpoint at the last check (differs)no remote endpoint we checkAnswered with HTTP 404 (3 days 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

zeabur

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

CLI skills for deploying, managing, and troubleshooting services on Zeabur — a cloud deployment platform. Covers the full lifecycle: project creation, service deployment, template management, domain registration & DNS, server provisioning, environment variables, logs, and common issue diagnosis.

Agent Lab Deploy

In its own words, on Official MCP Registry:

Deploy websites, apps, agents and MCP servers from Claude Code or Codex. OAuth, runs in Taiwan.

How to run each

zeabur As a Claude Code plugin

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

Agent Lab Deploy As a remote MCP server

Claude Code
claude mcp add --transport http agentlab-deploy https://mcp.agentlab.cresclab.com/mcp

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

Only Agent Lab Deploy 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: zeabur · What it can do: Agent Lab Deploy · 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