The MCP ecosystem often has several independent packages implementing the same tool — and "Database" currently has 13. 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 |
|---|---|---|---|---|---|---|
| Database Serverbest by mradovic95 | mcp-database-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Multi-Database (ahmetbarut) by ahmetbarut | @ahmetbarut/mcp-database-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| SQL Database (ADevGuide) by adevguide | @adevguide/mcp-database-server
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Universal Database by npm | mcp-database
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Database by Recordum | database-mcp-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Database by cocaxcode | @cocaxcode/database-mcp
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Database by nam088 | @nam088/mcp-database-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Multi-Database (TuringDance) by turingdance | @turingdance/database-mcp
npm |
A 98/100 | High | Source | 3 | 2026-07-22 |
| Database by TheRaLabs | database-mcp
PyPI |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Database by PyPI | database-mcp-server
PyPI |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Database by executeautomation | @executeautomation/database-server
npm |
A 98/100 | High | Source | 5 | 2026-07-22 |
| Database by nitaiaharoni1 | database-mcp
npm |
A 94/100 | Minimal | Source | 1 | 2026-07-22 |
| Multi-Database (adversity) by adversity | @adversity/mcp-database
npm |
A 91/100 | 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.