modelcontextprotocol/servers
Read the upstream summary on the left, browse the cached forks below it, and load each fork comparison into the right-hand panel.
modelcontextprotocol/servers
`modelcontextprotocol/servers` is the official MCP reference-servers repository. It is active, popular, and intentionally focused on small reference implementations rather than production-ready products. Forks are most interesting if you want MCP examples, SDK usage patterns, or a starting point for building your own server, not if you want a maintained server catalog or polished end-user app.
Jump straight into Discofork's strongest cached fork picks, or open a compare view in one click.
Choose a fork to inspect
Prefer upstream unless you specifically need an older frozen snapshot; this fork adds no visible capabilities and is far behind current maintenance.
Choose this fork if you want the MCP reference servers plus extra distribution and AI-tooling metadata. Choose upstream if you want the latest server fixes and the cleanest reference baseline.
Prefer upstream unless you specifically need this frozen fork or its README-level customization. For adopters, the main signal is staleness: it adds little and misses substantial upstream progress.
Prefer upstream unless you specifically need this older snapshot; the fork adds no visible features and is far too stale for most adopters.
Prefer upstream unless you specifically want a frozen snapshot; this fork adds no visible capabilities and is materially behind on maintenance and recent improvements.
Prefer upstream unless you specifically need this exact historical snapshot; the fork adds no visible value and is far behind current fixes and capabilities.
Prefer upstream unless you explicitly need this older snapshot; the fork adds no visible functionality and is materially behind current upstream maintenance.
Choose upstream unless you specifically need the added contributor-improvement script. This fork looks like a narrow maintenance helper, not a better reference-server distribution, and its lag behind upstream is the main adoption concern.