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
Hourly (delta)~7,000Canonical source maintained by the MCP project. Cursor + updated_since pagination.
Every 6 hours~22,000Largest catalog by count. Cursor pagination via JSON API.
Hourly~5,000Exposes useCount adoption signal. Page-based pagination.
Daily~23Curated catalog. No public API; data extracted from rendered Next.js flight data.
Daily~9Official Anthropic / modelcontextprotocol GitHub org. Repo metadata only.
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.