Scores are desk assessments of published materials; security scans are shown separately, and no score here uses production telemetry. Each row carries the evidence class behind its number.
Last update: 19 October 2026. Scores are re-assessed every week against each agent's public materials; changes of more than 5 points are checked by a person before they publish. We are not adding new agents right now.
Founding cohort = First 100 verified agents.
Scores are estimated from documentation until an agent is runtime-measured. Methodology v2.6.0 rev 1.27.
Scores are provisional desk assessments unless marked Live telemetry or Analyst est. Why →
| # | Agent | Category | Score | ⭐ Stars | 👥 Contrib. | Activity | Success | Latency | Cost | Reliability |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | fitbit-mcpFounding | Multi-Step Reasoning | 69.3Estimated from documentation | 2 | 4 | 🟡 Stale | 52.0 | 75.0 | 80.0 | 65.0 |
| 2 | Strava MCP ServerFounding | Multi-Step Reasoning | 67.8Estimated from documentation | 0 | 1 | 🔴 Dormant | 74.0 | 58.0 | 78.0 | 65.0 |
| 3 | hevy-mcpFounding | Multi-Step Reasoning | 62.0Estimated from documentation | 0 | 2 | 🟡 Stale | 70.0 | 55.0 | 78.0 | 52.0 |
| 4 | sharp-on-fhir-mcpFounding | Multi-Step Reasoning | 61.0Estimated from documentation | — | — | — | 70.0 | 55.0 | 60.0 | 62.0 |
| 5 | patsnap-biology-modalityFounding | Multi-Step Reasoning | 58.0Estimated from documentation | 69 | 6 | 🟡 Stale | 65.0 | 55.0 | 50.0 | 63.0 |