Novita vs Tuning Engines - Governed AI Runtime
Novita is an MCP server published by novitalabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). Tuning Engines - Governed AI Runtime is an MCP server published by cerebrixos-org. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-27. 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
| Marketplace |  Novita |  Tuning Engines - Governed AI Runtime |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:ddc904348d9e Forks (GitHub): 9 Pulls (Docker Hub): 10 747 Stars (Docker Hub): 0 Stars (GitHub): 12 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.4.34 Downloads/month (npm): 651 Downloads/week (npm): 77 Forks (GitHub): 4 (last published figure) Stars (GitHub): 6 (last published figure) 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 | Novita | Tuning Engines - Governed AI Runtime |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 12 | 6 (last published figure) |
| Pulls (Docker Hub) (differs) | 10 747 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 9 | 4 (last published figure) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (mcp/novita) | On your machine (tuningengines-cli) |
| Transport | stdio | stdio |
| Tools it declares (differs) | 20 | Not published |
| Environment variables it asks for (differs) | 1, secrets among them: 0 | 1, secrets among them: 1 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/novitalabs/novita-mcp-server | github.com/cerebrixos-org/tuning-engines-cli |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
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
Novita
Seamless interaction with Novita AI platform resources.
Tuning Engines - Governed AI Runtime
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
How to run each
Novita As a local MCP server: Docker image
claude mcp add --transport stdio novita -- docker run -i --rm mcp/novitaTuning Engines - Governed AI Runtime As a local MCP server: npm package
claude mcp add --env "TE_API_KEY=<YOUR_TE_API_KEY>" --transport stdio tuning-engines -- npx -y tuningengines-cli mcp serveRequires: TE_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of Tuning Engines - Governed AI Runtime publish no list of tools, so we do not compare tools.
Settings each asks for
Only Novita asks for
NOVITA_API_KEY
Only Tuning Engines - Governed AI Runtime asks for
TE_API_KEY (secret)
Settings as each marketplace publishes them. Asking for fewer is not better in itself.
What it can do: Novita · What it can do: Tuning Engines - Governed AI Runtime · Compare two other plugins
Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. 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 . We publish no contact details for plugin publishers.