Eval Skills vs io.github.kubeshop/testkube-mcp
Eval Skills is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑27.
Eval Skills is a plugin bundle for AI coding tools published by Confident AI. No marketplace we read lists it any more. 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 2026-10-27. 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
| Marketplace |  io.github.kubeshop/testkube-mcp | |
|---|---|---|
| Community marketplace confident-ai/eval-skills | Removed on 2026-10-27 Version: 1.1.0 Forks (GitHub): 1 Stars (GitHub): 11 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 2.14.2 Forks (GitHub): 180 Stars (GitHub): 1 674 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:43aa88f2d416 Forks (GitHub): 180 Pulls (Docker Hub): 34 027 Stars (Docker Hub): 0 Stars (GitHub): 1 674 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
| Fact | Eval Skillsno longer listed · | io.github.kubeshop/testkube-mcp |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 2 |
| Stars (GitHub) (differs) | 11 | 1 674 |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 34 027 |
| Forks (GitHub) (differs) | 1 | 180 |
| Last release (differs) | Not published | 2026-10-19 |
| Where it runs (differs) | Installs as a plugin bundle | Remote server or your machine |
| Transport (differs) | Not stated | Streamable HTTP, stdio |
| Tools it declares (differs) | Not published | 28 |
| Environment variables it asks for (differs) | Not published | 9, secrets among them: 1 |
| Parts of the bundle (differs) | 10 | Not a bundle |
| Licence (differs) | Apache-2.0 | NOASSERTION |
| Repository (differs) | github.com/confident-ai/eval-skills | github.com/kubeshop/testkube |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-10-15 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 5 days ago, requires a key |
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 Eval Skills
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Scaffolding, running, documenting, and publishing AI evaluations. Ships skills and commands for setting up eval workspaces, creating custom evals (or adapting existing…
-
Decide, design, gate, judge, and defend evaluations for LLM, agent, and retrieval systems. Not ordinary unit tests.
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
-
Compare AI coding skills head-to-head to find which one works best for your task. Run controlled A/B tests: same model (Claude Code), same tasks, different skills. Each candidate…
What each says it does
Eval Skills
Skills that take a coding agent from your first trace to evals you can trust: error analysis, datasets, validated graders, eval runs, and production monitoring.
io.github.kubeshop/testkube-mcp
MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
How to run each
Eval Skills
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
io.github.kubeshop/testkube-mcp As a local MCP server: Docker image
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/testkubeRequires: 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 Eval Skills publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of Eval Skills publish no settings it asks for, so we do not compare settings.
What it can do: Eval Skills · What it can do: io.github.kubeshop/testkube-mcp · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. 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.