Python Implementation of the Registry?

[SinOverCos]

Wondering if it's on the roadmap to implement this registry as a python library instead of a golang service?

I'm looking to host an internal MCP registry and don't have a lot of experience in golang. All of my company's GenAI stack is written in python and it's a bit awkward trying to get this golang service to fit nicely into our existing python ecosystem.

Sort of related, what's the recommendation for adding some company-specific logic to this registry service? I was planning to add some features specific to my situation and probably doesn't make sense to be upstreamed. I'd like to keep everything in python as much as possible so I was thinking of running this golang service an my own wrapper service side by side. Have clients talk to my wrapper service and my wrapper service will talk to this golang service and e.g. change the response a bit before returning stuff back to the client.

[connor4312]

See: #11

Reusability of infrastructure, implementation detail decisions: While we expect the ecosystem to reuse the shapes (such as OpenAPI shape, mcp.json shape) associated with this work, we are not designing for reuse of the underlying implementation details and infrastructure. As such, we will not provide instructions on "how to serve your own instance of this metaregistry".

The registry include a spec, and you are free to implement your own registry in the language (and database) of your choosing, but the goal of this repo isn't to provide an end-all implementation that is deployable in every architecture.