github
saferskills
The VirusTotal of AI agents — free, public, open-source trust scoring for skills, MCP servers, hooks, and plugins. Apache-2.0. saferskills.ai
76fair
▣ Overview
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
100
35.0
Freshness
25%
100
25.0
Adoption
20%
7
1.4
Quality
10%
100
10.0
Trust
10%
50
5.0
Total
76.4
⚿ Capabilities & Risk Explainer
fs readfs writenetworkexecevalsecrets
◆ Risk level: high
fs read + fs write + network + exec + eval + secrets active — can execute code, access credentials, and make external network calls.
⚙ Install config
Claude Desktop · Cursor · Windsurf · VS Code (Copilot) · Claude Code
add to your MCP client config:
{
"mcpServers": {
"saferskills": {
"command": "npx",
"args": [
"-y",
"saferskills"
]
}
}
}📈 Score historylast 32 snapshots
5/26/20267/21/2026 · 32 snapshots
⚙ Maintenance health
maintenance data not yet available — check back later.
⛁ Raw data
weekly downloads0
github stars7
forks0
open issues5
license✓ present
readme length13521 chars
last publish2d ago
last commit0d ago
last updated18d ago
owner of this server? claim your listing to get a verified badgeclaim →
🔔 Score drop alerts
get notified by email when this server's score drops 5+ points