Ext Ops Panel
Open dashboard
Comparison

critical-thinking-tools vs io.github.kubeshop/testkube-mcp

critical-thinking-tools is a plugin bundle for AI coding tools published by cognitive-bias-lab. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.kubeshop/testkube-mcp is an MCP server published by kubeshop. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-10-29. 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
Marketplacecritical-thinking-toolsio.github.kubeshop/testkube-mcp
Claude Code: claude-plugins-community Listed
Version: 9447e4a
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 2.15.0
Forks (GitHub): 180
Stars (GitHub): 1 677
Not marked · First seen
Docker MCP Catalog Not listed Listed
Version: sha256:43aa88f2d416
Forks (GitHub): 180
Pulls (Docker Hub): 34 097
Stars (Docker Hub): 0
Stars (GitHub): 1 677
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

critical-thinking-tools vs io.github.kubeshop/testkube-mcp
Factcritical-thinking-toolsio.github.kubeshop/testkube-mcp
Marketplaces that list it (differs)1 (worse)2 (better)
Stars (GitHub) (differs)0 (worse)1 677 (better)
Pulls (Docker Hub) (differs)No figure on Docker Hub34 097
Forks (GitHub) (differs)0 (worse)180 (better)
Last release (differs)Not published2026-10-29
Where it runs (differs)Installs as a plugin bundleRemote server or your machine
Transport (differs)Not statedStreamable HTTP, stdio
Tools it declares (differs)Not published28
Environment variables it asks for (differs)Not published7, secrets among them: 2
Licence (differs)Not statedNOASSERTION
Repository (differs)github.com/cognitive-bias-lab/cognitive-bias-lab-pluginsgithub.com/kubeshop/testkube
Changes in the last 7 days (differs)03
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkResponded 14 h ago, requires a key

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

critical-thinking-tools

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

Critical Thinking Tools is a science-backed Claude Code plugin from Cognitive Bias Lab that helps users reason more clearly about decisions, beliefs, plans, forecasts, and disagreements. It provides structured thinking workflows based on research in psychology, decision science, forecasting, intelligence analysis, and debiasing. The plugin includes 12 practical tools: devil’s advocate review, pre-mortem analysis, outside-view forecasting, competing hypotheses, consider-the-opposite, steelmanning, Socratic questioning, base-rate audits, causal story dissection, calibration forecasting, decision journals, and groupthink red-team checks. Each tool guides Claude to produce structured outputs with likely bias risks, evidence that would change the conclusion, next actions, and a short science note. The plugin is designed as a practical judgment aid, not a guarantee of unbiased thinking, and emphasizes uncertainty, evidence updates, and careful reasoning.

io.github.kubeshop/testkube-mcp

In its own words, on Official MCP Registry:

MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants

How to run each

critical-thinking-tools As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install critical-thinking-tools@claude-community

io.github.kubeshop/testkube-mcp As a local MCP server: Docker image

Claude Code
claude mcp add --env "TK_ACCESS_TOKEN=<YOUR_TK_ACCESS_TOKEN>" --env "TK_ENV_ID=<YOUR_TK_ENV_ID>" --env "TK_ORG_ID=<YOUR_TK_ORG_ID>" --transport stdio testkube -- docker run -i --rm -e TK_ACCESS_TOKEN -e TK_ENV_ID -e TK_ORG_ID mcp/testkube

Requires: TK_ACCESS_TOKEN (secret), TK_ENV_ID (secret), TK_ORG_ID (secret)

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

Only io.github.kubeshop/testkube-mcp has a remote endpoint we check. How we check endpoints

Tools each declares

The marketplaces of critical-thinking-tools publish no list of tools, so we do not compare tools.

Settings each asks for

The marketplaces of critical-thinking-tools publish no settings it asks for, so we do not compare settings.

What it can do: critical-thinking-tools · What it can do: io.github.kubeshop/testkube-mcp · 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. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. 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