25
/100
F
◉ Complete 5⁄5
AgentShield
Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.
Glama
Ambiguous Schemas
Exfiltration Risk
Complete visibility
— 5/5 applicable dimensions scored
✓ Schema Quality
✓ Protocol
— Reliability
✓ Docs & Maintenance
✓ Security Hygiene
✓ Schema Interpretability
Schema Quality
90
25% weight
Protocol Compliance
35
20% weight
Reliability
—
20% weight
Docs & Maintenance
77
15% weight
Security Hygiene
67
20% weight
Schema Interpretability
83
15% weight
Score History
Category Trends
30-Day Uptime
30 days ago
Today
Static Analysis
| Metric | Score | Rating |
|---|---|---|
| Schema Completeness | 100 | Good |
| Description Quality | 75 | Good |
| Documentation Coverage | 72 | Good |
| Maintenance Pulse | 71 | Good |
| Dependency Health | 75 | Good |
| License Clarity | 100 | Good |
| Version Hygiene | 80 | Good |
Analyzed 1 month ago
Add this to your README to display your MCP Scoreboard grade:
