MCPRadar Security Leaderboard

Independent security scores for MCP servers — sourced from the official registry

How scores work ▾

AIVSS (AI Vulnerability Scoring System) rates MCP server security on a 0–10 scale where 0 = safe and 10 = critical.


The score combines severity-weighted findings (critical×10, high×7, medium×4, low×1) divided by tool count, multiplied by a density factor (capped between 0.5× and 2.0×). The result is clamped to 10.0 and mapped to a letter grade:


A 0.0–0.9   B 1.0–2.9   C 3.0–4.9   D 5.0–6.9   F 7.0–10.0


Hash: SHA-256 of the alphabetically sorted tool names — used to detect tool-list changes across scans (drift detection).


Scope: schema = tool schemas analyzed, fingerprint = tool signature comparison, cve = known-vulnerability matching against OSV/GitHub Advisory.

Loading…
Grade:
Rank Server Risk 0→10 Grade Scope Tools Findings Scanned Hash