METHODOLOGY
How MCP Toplist ranks servers
Every Model Context Protocol server gets a composite score derived from four signals. All four are log-normalized so that one large repo doesn't dominate the ranking, and so that older, multi-version, actively-maintained servers can compete on their own merits.
SCORE COMPONENTS
Composite score weights
| Signal | Weight | Source |
|---|---|---|
| GitHub stars | 35% | GitHub REST API, log10-scaled |
| Version count | 25% | Distinct versions across all registries |
| Release activity | 25% | Commits in last 30 days + 3× releases in last 90 days |
| Listing age | 15% | Months since first publish, log10-scaled |
UPDATE CADENCE
How often the data refreshes
Each registry has its own sync job. Rankings reflect the most recent data from every source. See /sources for the full table.
- · Official MCP Registry — hourly delta sync
- · Smithery — hourly
- · Glama — every 6 hours
- · mcp.so — daily
- · GitHub modelcontextprotocol org — daily
- · GitHub stars and commit signals — daily refresh via the feature builder job
LIMITATIONS
What the score does not measure
- Code quality. The composite score is a popularity and activity signal, not a quality assessment.
- End-user adoption. Some registries expose usage counts (Smithery's
useCount); others don't. We don't blend usage into the score because coverage is uneven. - Security or trust.A high score doesn't imply a server is safe to run. Always review the repository before installing.
- Servers without a public repository.Stars and commit activity terms collapse to zero, so closed-source or repo-less servers will rank low even if they're widely used.