ARC-1 vs Codebase Memory MCP
Both are Grade A and 3.6 points apart, so choose on what you weigh most. ARC-1 leads on supply-chain integrity; Codebase Memory MCP leads on transparency and adoption.
Choose ARC-1 if supply-chain integrity matters most.
- +2.1Safety / Integrity: 100% of recent commits signed, against 31%
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.
Choose Codebase Memory MCP if transparency and adoption matter most.
- +6.4Adoption: 12.1k weekly downloads against 2.2k
- +0.9Transparency: OSSF Scorecard 8.0 against 7.0
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of ARC-1 and Codebase Memory 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.
Full evidence
| Signal | ARC-1arc-mcp/arc-1 | Codebase Memory MCPDeusData/codebase-memory-mcp |
|---|---|---|
| HVTrust score | 88.4 | 92.0 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #56 | #13 |
| Rank in MCP Servers | #15 | #3 |
| GitHub stars | 264 | 49.0k |
| Last updated | today | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.0 / 10 | 8.0 / 10 |
| License | MIT | MIT |
| Downloads | 2k/wk | 12k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 21.2 | 19.1 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.4 | 15.3 |
| Maintenance / 20 | 20.0 | 19.9 |
| Adoption / 20 | 10.3 | 16.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — Anthropic | 1 — Anthropic |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| 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 v4.4 →