mcp-proxy vs MCP Python SDK
MCP Python SDK leads on trust: 95.0/100 (Grade A) against 85.9/100 (Grade A), a 9.1-point gap. MCP Python SDK leads on supply-chain integrity and adoption.
A bridge between Streamable HTTP and stdio MCP transports
mcp-proxy doesn't lead on any scored dimension in this pair.
The official Python SDK for Model Context Protocol servers and clients
Choose MCP Python SDK if supply-chain integrity and adoption matter most.
- +5.1Adoption: 64.5M weekly downloads against 97k
- +4.4Safety / Integrity: 100% of recent commits signed, against 56%
- +1.5Transparency: OSSF Scorecard 7.8 against 6.0
- +1.4Maintenance: last push 1d ago, against 4d ago
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of mcp-proxy and MCP Python SDK, two Protocols & Tool Integration projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | mcp-proxysparfenyuk/mcp-proxy | MCP Python SDKmodelcontextprotocol/python-sdk |
|---|---|---|
| HVTrust score | 85.9 | 95.0 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #81 | #2 |
| Rank in Protocols & Tool Integration | #7 | #1 |
| GitHub stars | 2.8k | 24.6k |
| Last updated | 4d ago | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.0 / 10 | 7.8 / 10 |
| License | MIT | MIT |
| Downloads | 97k/wk | 64.5M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.8 | 22.2 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.6 | 15.1 |
| Maintenance / 20 | 17.0 | 18.4 |
| Adoption / 20 | 14.9 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | — |
| Requires API keys | Yes | No |
| Plugin surface | — | extensions |
| 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 →