CompletionKit vs classifier.dev
CompletionKit is an MCP server published by completionkit.com. Marketplaces we read that list it: 1 (Official MCP Registry). classifier.dev is an MCP server published by classifier.dev. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-14. 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 |  CompletionKit |  classifier.dev |
|---|---|---|
| Official MCP Registry | Listed Version: 1.0.0 Forks (GitHub): 1 Stars (GitHub): 3 Not marked · First seen |
Listed Version: 1.0.0 Forks (GitHub): 33 Stars (GitHub): 425 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 | CompletionKit | classifier.dev |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 3 (worse) | 425 (better) |
| Forks (GitHub) (differs) | 1 (worse) | 33 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Remote server (completionkit.com/mcp) | Remote server (classifier.dev/mcp) |
| Transport | Streamable HTTP | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Licence | Not stated | Not stated |
| Repository (differs) | github.com/homemade-software-inc/completion-kit | github.com/mrmps/classifier-dev |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | not checked yet | Responded 32 h ago |
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
CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
classifier.dev
Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.
How to run each
CompletionKit As a remote MCP server
claude mcp add --transport http evals https://completionkit.com/mcp --header "Authorization: Bearer <YOUR_TOKEN>"Requires: Authorization header
classifier.dev As a remote MCP server
claude mcp add --transport http classifier https://classifier.dev/mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only classifier.dev has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: CompletionKit · What it can do: classifier.dev · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.