Ext Ops Panel
Open dashboard
Comparison

iris-eval vs Opik

iris-eval is a plugin bundle for AI coding tools published by Iris. Marketplaces we read that list it: 1 (Community GitHub marketplaces). Opik is an MCP server published by comet-ml. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-10-16. 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
Marketplaceiris-evalOpik
Community marketplace iris-eval/mcp-server Listed
Version: 0.20.0
Forks (GitHub): 4
Stars (GitHub): 9
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 3.0.5
Downloads/month (PyPI): 3 591
Downloads/week (PyPI): 1 906
Forks (GitHub): 38
Stars (GitHub): 222
Not marked · First seen
Docker MCP Catalog Not listed Listed
Version: sha256:0e0d7d33d5eb
Forks (GitHub): 38
Pulls (Docker Hub): 16 974
Stars (Docker Hub): 1
Stars (GitHub): 222
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

iris-eval vs Opik
Factiris-evalOpik
Marketplaces that list it (differs)1 (worse)2 (better)
Stars (GitHub) (differs)9 (worse)222 (better)
Pulls (Docker Hub) (differs)No figure on Docker Hub16 974
Forks (GitHub) (differs)4 (worse)38 (better)
Last releaseNot publishedNot published
Where it runs (differs)On your machine (@iris-eval/mcp-server)Remote server or your machine
Transport (differs)Not statedStreamable HTTP, stdio
Tools it declares (differs)Not published13
Environment variables it asks for (differs)Not published4, secrets among them: 1
Parts of the bundle (differs)2Not a bundle
Licence (differs)Not statedApache-2.0
Repository (differs)github.com/iris-eval/mcp-servergithub.com/comet-ml/opik-mcp
Changes in the last 7 days (differs)20
First seen (differs)2026-10-132026-10-11
Endpoint at the last check (differs)no remote endpoint we checkResponded 22 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

iris-eval

In its own words, on Community GitHub marketplaces:

Stop shipping agents on vibes — agent eval for any MCP workflow. Score output quality, catch PII and prompt injection, verify citations, and enforce cost budgets. 12 MCP tools + the iris-eval skill.

Opik

In its own words, on Official MCP Registry:

Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

How to run each

iris-eval As a Claude Code plugin

Claude Code
/plugin marketplace add iris-eval/mcp-server
/plugin install iris-eval@iris-eval

Opik As a remote MCP server

Claude Code
claude mcp add --transport http opik-mcp https://www.comet.com/opik/api/v1/mcp

Requires: OPIK_API_KEY (secret)

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

Only Opik has a remote endpoint we check. How we check endpoints

Tools each declares

The marketplaces of iris-eval publish no list of tools, so we do not compare tools.

Settings each asks for

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

What it can do: iris-eval · What it can do: Opik · 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.

Where the data comes from: how the catalog is built