The MCP ecosystem often has several independent packages implementing the same tool — and "Create" currently has 8. 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 |
|---|---|---|---|---|---|---|
| Create Source verifiedbest by mcpdotdirect | @mcpdotdirect/create-mcp-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Create by JoshuaKGoldberg | create
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Create by yoav0gal | mcp-create
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Create Official by modelcontextprotocol | @modelcontextprotocol/create-server
npm |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Create by npm | create-mcp-server
npm |
A 98/100 | Minimal | Metadata | 1 | 2026-07-22 |
| Create by formbridge | @formbridge/create
npm |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Create by modelcontextprotocol | create-mcp-server
PyPI |
A 98/100 | High | Source | 2 | 2026-07-22 |
| Create by zueai | create-mcp
npm |
A 94/100 | High | Source | 3 | 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.