Live Tape · Loading market feed
MCPHERE
What is MCP?ServersTrendingSignalsCompareReports
...
  1. Home
  2. Intelligence
  3. How We Rank
MCPHEREDecision-grade MCP intelligence
What is MCP?ServersCompareInsightsReportsResourcesMethodologySubmitSponsorPrivacyTermsCookies
Live Tape · Live MCP registryUpdated recently

How We Rank MCPs

Our intelligence model blends multiple repository and ecosystem signals to estimate momentum and reliability. We intentionally do not publish exact weighting rules to protect model integrity and reduce score gaming.

Open All IndexedOpen PublishedOpen Trending

All Indexed

This is the broadest surface. It includes all non-rejected records we have indexed, including records that are still under review for public visibility.

Published

This is the curated public subset. Records here passed the public eligibility gate and are safe to expose as the external-facing shortlist.

Trending

This is a published-only momentum surface. It is optimized for discovery of breakouts and risers, not total inventory coverage.

Growth Velocity

We evaluate short-term and medium-term growth trends to detect sustained momentum versus one-time spikes.

Activity Recency

We prioritize projects that show recent and consistent maintenance activity across repository and release lifecycle.

Ecosystem Engagement

Contributor participation and collaboration patterns are used as quality-of-engagement signals.

Operational Confidence

Health, anomaly checks, and historical consistency improve confidence in score reliability.

Published Gate And Health Normalization

Public visibility is stricter than indexing. A server can be indexed but still remain outside the public subset until it clears quality, health, and review guardrails. Legacy health labels are normalized into a single automated status set: healthy, warning, at_risk, abandoned.

Update Pipeline

  1. Snapshot repository metrics into current metrics and historical snapshots.
  2. Backfill or refresh metric deltas so short-window momentum has reliable inputs.
  3. Recompute automated health to normalize health tiers across servers and scores.
  4. Recalculate scores and momentum labels on a consistent batch cadence.

Transparency Principles

  • Sponsor and partner flags never increase ranking score.
  • Badges are assigned from score distribution, production-readiness, and momentum context.
  • Scores are updated in batch cycles for consistent cross-project comparison.
  • Indexed, published, and trending are intentionally different surfaces with different inclusion rules.