Tadas Antanavicius
Tadas Antanavicius
As per #39, official registry consumers will have long tail needs for other kinds of data with which they want to enrich their mirrors of the registry, while maintaining compatibility...
We currently rely on GitHub OAuth for the following reasons: - At a baseline, as a simple IdP, so we have a notion of "users" - For its organization capabilities,...
Adding more up-to-date documentation to address #131: > We are starting to get a lot of repeat questions that we have answers to scattered throughout docs and issues. The designs...
Discussed in https://github.com/modelcontextprotocol/registry/discussions/118 It seems reasonable to encourage a convention of putting `server.json` in the root of an MCP package artifact. There are a number of plausible benefits like defining...
@dmartinol [pointed out](https://github.com/modelcontextprotocol/registry/issues/123#issuecomment-2966939920) that we have an `unknown` value in the `registry_name` seed data [here](https://github.com/modelcontextprotocol/registry/blob/686fbe1e78117546c91dfb47051e405f0bd1762b/data/seed_2025_05_16.json#L6180C9-L6180C35). `registry_name` should be specifically one of the supported registries; unknown should not be permitted.
As @connor4312 has pointed out, we are starting to get a lot of repeat questions that we have answers to scattered throughout docs and issues. The designs in the [initial...
The Official Registry API should be a subset of the MCP Registry API OpenAPI Schema. At the moment, the [OpenAPI schema in the repo](https://github.com/modelcontextprotocol/registry/blob/686fbe1e78117546c91dfb47051e405f0bd1762b/docs/openapi.yaml) is trying to represent both. For...
This is a first cut at properly defining the `server.json` file. We have been working out details of the shape for a while, but to-date it has only been implicitly...
As discussed with @modelcontextprotocol/core-maintainers in a recent nomination thread, we want to empower Working/Interest Groups to grow their own maintainer pools. The one line being added is: > - If...
See: https://discord.com/channels/1358869848138059966/1369487942862504016/1425290448548921436 We should offer a CLI-based mechanism for authenticated publishers to mark an entire server (i.e. all versions of a `name`) as `deprecated` status. We should also include clear...