Comparison

Zen vs red-agent

red-agent is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑17.

Zen is an MCP server published by BeehiveInnovations. Marketplaces we read that list it: 1 (Docker MCP Catalog). red-agent is a plugin bundle for AI coding tools published by Red Agent Team. No marketplace we read lists it any more. As of our marketplace pass on 2026-10-22. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplace	Zen	red-agent
Docker MCP Catalog	Listed Version: sha256:02cbe1d325db Forks (GitHub): 1 036 Pulls (Docker Hub): 34 970 Stars (Docker Hub): 0 Stars (GitHub): 11 799 Not marked · First seen 2026-10-11	Not listed
Community marketplace abossenbroek/abossenbroek-claude-plugins	Not listed	Removed on 2026-10-17 Version: 1.7.0 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen 2026-10-15

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

Zen vs red-agent
Fact	Zen	red-agentno longer listed · 2026-10-17
Marketplaces that list it (differs)	1	0
Stars (GitHub) (differs)	11 799	2
Pulls (Docker Hub) (differs)	34 970	No figure on Docker Hub
Forks (GitHub) (differs)	1 036	0
Last release	Not published	Not published
Where it runs (differs)	On your machine (mcp/zen)	Installs as a plugin bundle
Transport (differs)	stdio	Not stated
Tools it declares (differs)	18	Not published
Environment variables it asks for (differs)	4, secrets among them: 4	Not published
Parts of the bundle (differs)	Not a bundle	14
Licence (differs)	NOASSERTION	Not stated
Repository (differs)	github.com/beehiveinnovations/zen-mcp-server	github.com/abossenbroek/abossenbroek-claude-plugins
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. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of red-agent

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

SecurityScan

Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

by apisecurityscan.net · MCP server

Listed on: Official MCP Registry · Describes nearly the same job
Trent

Security reviews, threat models over a repo or website, and remediation tracking, in your editor.

by trent.ai · MCP server

Listed on: Official MCP Registry, Community GitHub marketplaces · Describes nearly the same job
claude-security

Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the…

by Anthropic · Plugin bundle

Listed on: Claude Code: claude-plugins-official · Describes nearly the same job
skill-security

Security audit toolkit for Claude Code skills and plugins — detects prompt injection, backdoors, and permission escalation before installation

by Michael McCabe · Plugin bundle

Listed on: Community GitHub marketplaces · Describes nearly the same job
security-guidance

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…

by Anthropic · Plugin bundle

Listed on: Claude Code: claude-plugins-official, Claude: knowledge-work-plugins · Describes nearly the same job
Semgrep Guardian

Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.

by semgrep · Plugin bundle

Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

Zen

In its own words, on Docker MCP Catalog:

Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.

red-agent

In its own words, on Community GitHub marketplaces:

Adversarial red/rainbow team analysis plugin for Claude Code. Finds weaknesses in LLM interactions through systematic probing using a 10x10 attack taxonomy (11 categories for PR analysis including code-duplication). Includes automated fix orchestrator with GitHub integration, PR analysis with 4 git modes, and comprehensive security documentation.

How to run each

Zen As a local MCP server: Docker image

Claude Code

claude mcp add --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "XAI_API_KEY=<YOUR_XAI_API_KEY>" --transport stdio zen -- docker run -i --rm -e GEMINI_API_KEY -e OPENAI_API_KEY -e OPENROUTER_API_KEY -e XAI_API_KEY mcp/zen

Requires: GEMINI_API_KEY (secret), OPENAI_API_KEY (secret), OPENROUTER_API_KEY (secret), XAI_API_KEY (secret)

red-agent

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

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

Tools each declares

The marketplaces of red-agent publish no list of tools, so we do not compare tools.

Settings each asks for

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

What it can do: Zen · What it can do: red-agent · 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 2026-10-22. We publish no contact details for plugin publishers.