Playwright MCP vs Stripe Agent Toolkit
Playwright MCP leads on trust: 91.6/100 (Grade A) against 84.6/100 (Grade A), a 7.0-point gap. Playwright MCP leads on supply-chain integrity and adoption; Stripe Agent Toolkit leads on maintenance.
Playwright MCP server
Choose Playwright MCP if supply-chain integrity and adoption matter most.
- +6.5Adoption: 9.0M weekly downloads against 18.4k
- +3.3Safety / Integrity: 100% of recent commits signed, against 29%
One-stop shop for building AI-powered products and businesses with Stripe.
Choose Stripe Agent Toolkit if maintenance matters most.
- +1.1Maintenance: last push today, against 3d ago
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
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.
Full evidence
| Signal | Playwright MCPmicrosoft/playwright-mcp | Stripe Agent Toolkitstripe/ai |
|---|---|---|
| HVTrust score | 91.6 | 84.6 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #11 | #95 |
| Rank in MCP Servers | #2 | #34 |
| GitHub stars | 38.0k | 1.9k |
| Last updated | 3d ago | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 5.9 / 10 | 6.1 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 9.0M/wk | 18k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 19.9 | 16.6 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.5 | 13.7 |
| Maintenance / 20 | 17.0 | 18.1 |
| Adoption / 20 | 20.0 | 13.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | 3 — Anthropic, Google Gemini, OpenAI |
| Requires API keys | No | No |
| Plugin surface | — | 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 →