SOURCES

Data sources

MCP Toplist aggregates Model Context Protocol servers from five active registries. Each registry has its own sync schedule. Cross-registry deduplication uses a SHA256 of the canonical repository URL or package identifier.

RegistryCadenceApprox. countNotes
Twice daily (delta)~27,000Canonical source maintained by the MCP project. Cursor + updated_since pagination.
Twice daily~83,000Largest catalog by count. Cursor pagination via JSON API.
Twice daily~5,300Exposes useCount adoption signal. Page-based pagination.
Twice daily~21,000Curated catalog. No public API; data extracted from the public sitemap and listing pages.
Twice daily~22,000Cursor-paginated JSON API. Provides GitHub stars, package registry, and remote transport metadata.
OBSERVATORY

Live measurements of each registry

The approximate counts above are a snapshot. The registry observatory shows the live catalog size, the time of the last successful sync, a 30-day trend and the known caveats for every registry in this table, refreshed twice daily with the pipeline.

Open the registry observatory →
DEDUPLICATION

How servers are matched across registries

A canonical key is computed for each server in priority order:

  1. Repository URL (normalized, lowercased)
  2. Package identifier (first package in packages[])
  3. Server name (fallback)

The SHA256 of the canonical identifier becomes the server's persistent ID. Two registries listing the same GitHub repo collapse to a single entry on MCP Toplist.

CORRECTIONS

Wrong mapping? Missing data?

Email hello@biff.ai with the server name and what should change. Most issues stem from duplicate registry entries that resolve themselves on the next sync.