MCP Trust Score

[Matvey-Kuk]

Hi!

This PR adds the "Trust Score" badge from our new Open Source MCP catalog.

Our catalog evaluates MCP servers based on technical quality—like protocol feature implementation and dependency health—rather than vanity metrics like GitHub stars.

The scoring process is fully transparent and reproducible:

• Evaluation Script: https://github.com/archestra-ai/website/blob/main/app/app/mcp-catalog/scripts/evaluate-catalog.ts
• Your Server's Page: https://archestra.ai/mcp-catalog/joshuayoes__ios-simulator-mcp

The badge is designed to be respectful to the structure of your readme, example:

Projects like Grafana MCP (https://github.com/grafana/mcp-grafana) are already participating.

We believe that transparent and truly open source MCP catalog should help the community to identify great MCP servers like yours 😊

We'd appreciate your support by merging this PR!

[joshuayoes]

So I'm looking at my rating on my server page and I had a few questions:

My server could probably support the Root part of the MCP spec, which I've opened an issue about, but the OAuth2 Auth, Prompts, Sampling, and HTTP Transport parts do not make sense for this server use case. I don't exactly want to put a score on my project that rates a server poorly for not implementing MCP features that don't make sense to support.

It seems the GitHub community score is also off based on your calculation it should be 16.
Stars scoring (0-10 points): >1000: 10 points
Contributors scoring (0-6 points): 4-10: 4 points
Issues scoring (0-4 points): 6-20: 2 points

I see that I can edit it here if I was to add this badge, first I'd want to make a way to mark that protocol_features will not be supported in a server without dinging a trust score.