Codebase Memory MCP vs Safari MCP
An independent, evidence-based trust comparison of Codebase Memory MCP and Safari MCP, two MCP Servers projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Codebase Memory MCP leads on trust — 91.0/100 (Grade A) vs 86.0/100 (Grade A), a 5.0-point gap. Full breakdown below.
| Signal | Codebase Memory MCPDeusData/codebase-memory-mcp | Safari MCPachiya-automation/safari-mcp |
|---|---|---|
| HVTrust score | 91.0 | 86.0 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #7 | #48 |
| Rank in MCP Servers | #1 | #7 |
| GitHub stars | 40.9k | 177 |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.5 / 10 | 6.1 / 10 |
| License | MIT | MIT |
| Downloads | 5k/wk | 2k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 18.4 | 19.1 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.9 | 13.7 |
| Maintenance / 20 | 20.0 | 19.4 |
| Adoption / 20 | 15.9 | 9.8 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | — |
| Requires API keys | No | No |
| Plugin surface | — | — |
| Provenance drift | Match | Match |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →