The MCP ecosystem often has several independent packages implementing the same tool — and "Docker" currently has 14. Every one of them was scanned with the same deterministic engine, so the numbers below are directly comparable: the Trust Score (A–F), the capability blast radius, and how much of the package the scan could actually inspect. They are ranked by score; ties break toward unscoped, longer-established packages.
| Implementation | Package | Trust | Capability | Coverage | Findings | Scanned |
|---|---|---|---|---|---|---|
| Dockerbest by sondt2709 | docker-mcp
npm |
A 100/100 | Moderate | Source | 2 | 2026-07-22 |
| Docker Manager by ofershap | mcp-docker-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Docker (supernova123) by supernova123 | @supernova123/docker-mcp-server
npm |
A 100/100 | High | Source | 7 | 2026-07-22 |
| Docker by swartdraak | @swartdraak/docker-mcp-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Docker by adamdude828 | mcp-server-docker
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Docker by kenforthewin | docker-mcp-server
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Docker by hypnosis | @hypnosis/docker-mcp-server
npm |
A 100/100 | High | Source | 10 | 2026-07-22 |
| Docker Instances by npm | mcp-docker
npm |
A 98/100 | High | Source | 2 | 2026-07-22 |
| Docker by PyPI | docker-mcp
PyPI |
A 98/100 | High | Source | 2 | 2026-07-22 |
| Docker by ckreiling | mcp-server-docker
PyPI |
A 98/100 | High | Source | 3 | 2026-07-22 |
| Docker by pnmice | mcp-docker-server
PyPI |
A 98/100 | High | Source | 3 | 2026-07-22 |
| Docker by 0xshariq | @0xshariq/docker-mcp-server
npm |
A 98/100 | High | Source | 11 | 2026-07-22 |
| Docker by L337-org | docker-mcp-server
PyPI |
A 98/100 | High | Source | 14 | 2026-07-22 |
| Docker by alisaitteke | @alisaitteke/docker-mcp
npm |
A 94/100 | High | Source | 4 | 2026-07-22 |
A higher-ranked implementation is not "the official one" — ranking reflects only what the deterministic scan found in each published package. Open an implementation to read its individual findings with evidence, its scan history per version, and to grab an embeddable badge. Scores are automated opinions, recomputed on every rescan.