github
verity
LLM confidence scoring layer — multi-dimensional epistemic verification for source grounding, factual consistency, and claim accuracy across ChatGPT, Claude, Grok, Perplexity, and any LLM output.
71fair
▣ Overview
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
100
35.0
Freshness
25%
85
21.3
Adoption
20%
0
0.0
Quality
10%
100
10.0
Trust
10%
50
5.0
Total
71.2
⚿ Capabilities & Risk Explainer
fs readsecrets
◆ Risk level: low
fs read + secrets — requires access to credentials or environment secrets.
⚙ Install config
Claude Desktop · Cursor · Windsurf · VS Code (Copilot) · Claude Code
add to your MCP client config:
{
"mcpServers": {
"verity": {
"command": "uvx",
"args": [
"verity"
]
}
}
}📈 Score historylast 16 snapshots
5/25/20266/8/2026 · 16 snapshots
⚙ Maintenance health
24/ 100 · is this project alive?
contributors (1y)2
top contributor share57%
releases (1y)0
ci✗ none
⛁ Raw data
weekly downloads0
github stars0
forks4
open issues9
license✓ present
readme length14056 chars
last publish15d ago
last commit15d ago
last updated2d 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