Tadas Antanavicius
Tadas Antanavicius
To-do's: - [ ] Identify what services we need to set up for this (& who will fund them) - [ ] Implement Any alerting system should pipe to some...
Fields like `name, `description`, and anything else free-form in the `server.json` file should be strictly limited to minimum necessary content so as to limit the possible vectors for spam and/or...
As an anti-spam measure, we could have an LLM reviewing submissions and flagging abnormalities, perhaps with automated suggestions for the blacklists in #98.
Blocked on https://github.com/modelcontextprotocol/registry/issues/85 E.g. domain expires, someone else buys it; we'd need to make sure the old owners don't still have access. We'd should not invalidate historical packages that exist,...
This is a fallback in case we do we have spammers or other bad actors succeed in publishing malicious/spam content. This should be possible in some code in this repo...
Primary purpose: sunset the [modelcontextprotocol/servers README](https://github.com/modelcontextprotocol/servers/blob/main/README.md).
We should allow for MCP servers to be published without requiring them to be prefixed with a `io.github` name prefix (which is the default fallback). Work to be done here:...
Blocked on: https://github.com/modelcontextprotocol/registry/issues/94 Although a crude metric, it may be helpful to track "download counts" of every MCP server in the official registry. Only the official registry has insight into...
Discussion: https://github.com/modelcontextprotocol/registry/discussions/14 Blocked on https://github.com/modelcontextprotocol/registry/issues/87 Although we do not have a hard requirement to implement any sorting signals in the official registry implementation, we do likely want this in the...
Some discussion here: https://github.com/modelcontextprotocol/registry/issues/93 When someone publishes a malicious or spam server.json, we need a mechanism for getting it reported and taken down. While we can rely on existing source...