Kagi Search vs Graphlog Career
Kagi Search is an MCP server published by kagisearch. Marketplaces we read that list it: 1 (Docker MCP Catalog). Graphlog Career is an MCP server published by graphlog.ai. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-13. 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 |  Kagi Search |  Graphlog Career |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:c26439346cd6 Forks (GitHub): 52 Pulls (Docker Hub): 20 506 Stars (Docker Hub): 1 Stars (GitHub): 566 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 2.3.5 Forks (GitHub): 0 Stars (GitHub): 0 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 | Kagi Search | Graphlog Career |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 566 (better) | 0 (worse) |
| Pulls (Docker Hub) (differs) | 20 506 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 52 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (mcp/kagisearch) | Remote server (career.graphlog.ai/mcp) |
| Transport (differs) | stdio | Streamable HTTP |
| Tools it declares (differs) | 2 | Not published |
| Environment variables it asks for (differs) | 2, secrets among them: 1 | Not published |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/kagisearch/kagimcp | github.com/foster-systems/graphlog-career |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-11 | 2026-11-06 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 23 h ago, requires authentication |
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
Kagi Search
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Graphlog Career
The career management plugin for your own AI assistant: CVs, cover letters, interviews and more.
How to run each
Kagi Search As a local MCP server: Docker image
claude mcp add --env "KAGI_API_KEY=<YOUR_KAGI_API_KEY>" --transport stdio kagisearch -- docker run -i --rm -e KAGI_API_KEY mcp/kagisearchRequires: KAGI_API_KEY (secret)
Graphlog Career As a remote MCP server
claude mcp add --transport http career https://career.graphlog.ai/mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only Graphlog Career has a remote endpoint we check. How we check endpoints
Tools each declares
The marketplaces of Graphlog Career publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of Graphlog Career publish no settings it asks for, so we do not compare settings.
What it can do: Kagi Search · What it can do: Graphlog Career · 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. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.