An independent, evidence-based trust comparison of Playwright MCP and Stripe Agent Toolkit, two MCP Servers projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
| Signal | Playwright MCPmicrosoft/playwright-mcp | Stripe Agent Toolkitstripe/ai |
|---|---|---|
| HVTrust score | 89.6 | 84.6 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #8 | #29 |
| Rank in MCP Servers | #1 | #3 |
| GitHub stars | 35.0k | 1.7k |
| Last updated | 4d ago | 3d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.6 / 10 | 5.9 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 6.4M/wk | 22k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.6 | 19.0 |
| Identity & provenance / 20 | 18.0 | 18.0 |
| Transparency / 17 | 14.1 | 13.5 |
| Maintenance / 20 | 13.7 | 16.2 |
| Adoption / 20 | 20.0 | 13.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | 2 — Anthropic, OpenAI |
| Requires API keys | No | No |
| Plugin surface | extensions | marketplace |
| 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 v4.2 →