scientific-debugging vs Opik
scientific-debugging is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑23.
scientific-debugging is a plugin bundle for AI coding tools published by iowarp. No marketplace we read lists it any more. Opik is an MCP server published by comet-ml. Marketplaces we read that list it: 3 (Official MCP Registry, Docker MCP Catalog, PyPI (MCP servers)). As of our marketplace pass on 2026-10-29. 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 |  Opik | |
|---|---|---|
| Community marketplace iowarp/clio-kit | Removed on 2026-10-16 Version: 0.3.1 Forks (GitHub): 5 Stars (GitHub): 8 Not marked · First seen |
Not listed |
| Community marketplace iowarp/clio-coder | Removed on 2026-10-23 Version: 0.3.2 Forks (GitHub): 5 Stars (GitHub): 8 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 3.0.8 Downloads/month (PyPI): 3 591 Downloads/week (PyPI): 814 Forks (GitHub): 37 Stars (GitHub): 225 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:0e0d7d33d5eb Forks (GitHub): 37 Pulls (Docker Hub): 17 268 Stars (Docker Hub): 1 Stars (GitHub): 225 Not marked · First seen |
| PyPI (MCP servers) | Not listed | Listed Version: 3.0.8 Downloads/month (PyPI): 3 591 Downloads/week (PyPI): 814 Forks (GitHub): 37 Stars (GitHub): 225 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 | scientific-debuggingno longer listed · | Opik |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 3 |
| Stars (GitHub) (differs) | 8 | 225 |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 17 268 |
| Forks (GitHub) (differs) | 5 | 37 |
| Last release (differs) | Not published | 2026-10-28 |
| 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 | 13 |
| Environment variables it asks for (differs) | Not published | 4, secrets among them: 1 |
| Licence | Apache-2.0 | Apache-2.0 |
| Repository (differs) | github.com/iowarp/clio-coder | github.com/comet-ml/opik-mcp |
| Changes in the last 7 days (differs) | 3 | 4 |
| First seen (differs) | 2026-10-13 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 12 h 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 scientific-debugging
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
misakanet io.github.Ikalus1988/misakanet
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
-
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
-
Agent Trace Triage is a Claude Code plugin for developers building agentic AI systems (LangGraph, CrewAI, custom tool loops, MCP agents). When an agent run fails, stuck in a loop…
-
Universal expert problem-solving agent specializing in complex debugging, mysterious runtime behavior, integration issues, and multi-layered technical challenges across any…
-
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
-
Flaky test detection, root cause analysis, and fix suggestions for development teams.
What each says it does
scientific-debugging
Diagnoses stalled or cross-system failures and wrong, NaN, nondeterministic, or unexpectedly slow scientific results through falsifiable hypotheses across distinct fault classes, with evidence-cited verdicts before any fix. Not for designing benchmarks or pre-registered experiments; use experiment-protocol.
Opik
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
How to run each
scientific-debugging
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Opik As a remote MCP server
claude mcp add --transport http opik-mcp https://www.comet.com/opik/api/v1/mcpRequires: 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 scientific-debugging publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of scientific-debugging publish no settings it asks for, so we do not compare settings.
What it can do: scientific-debugging · 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. Package data comes from the Python Package Index (pypi.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.