security
Security
Every MCP risk signal in one place — CVEs, tool safety, drift, naming, licenses. Heuristic: review signals, not verdicts. New here? The Risk tab gives an at-a-glance composite grade per server; the Code Analysis tab shows what the static scanner found in published source.
91 CRITICAL
7932 HIGH
2846 MEDIUM
4763 LOW
16 NONE
Risk: servers ranked by their composite exposure score — synthesised from CVEs, inferred permissions, drift, supply-chain and abandonment signals. Heuristic and banded; a high grade is a 'review this' signal, never a verdict.
A fix already ships upstream but the server still runs an older, vulnerable version — remediation lag, actionable today.
- agentfront/frontmcp HIGH CVE-2026-39885 1.5.2 → 2.3.0
- 1 E IBM/mcp-context-forge 100
- 2 E PrefectHQ/fastmcp 100
- 3 E dep0we/atomic-agents-stack 100
- 4 E koala73/worldmonitor 100
- 5 E awslabs/mcp 99
- 6 E sooperset/mcp-atlassian 99
- 7 E homeassistant-ai/ha-mcp 87
- 8 E n8n-mcp 86
- 9 E modelcontextprotocol/inspector 85
- 10 E clidey/whodb 84
- 11 E bytebase/dbhub 82
- 12 E memtomem/memtomem-stm 81
- 13 E @bike4mind/cli 80
- 14 E Bsh13lder/Lazy-Claw 80
- 15 E agentfront/frontmcp 80