65
/100
C
◎ Verified 4⁄4
avakill
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
Anthropic
LangChain
OpenAI
Links:
Verified visibility
— 4/4 applicable dimensions scored
✓ Schema Quality
✓ Protocol
— Reliability
✓ Docs & Maintenance
✓ Security Hygiene
— Schema Interpretability
Schema Quality
96
42% weight
Protocol Compliance
N/A
Local server
Reliability
N/A
Local server
Docs & Maintenance
82
25% weight
Security Hygiene
80
33% weight
Score History
Category Trends
Latest Health Check
Checked 3 weeks, 5 days ago
Static Analysis
| Metric | Score | Rating |
|---|---|---|
| Schema Completeness | 100 | Good |
| Description Quality | 90 | Good |
| Documentation Coverage | 87 | Good |
| Maintenance Pulse | 71 | Good |
| Dependency Health | 75 | Good |
| License Clarity | 100 | Good |
| Version Hygiene | 90 | Good |
Analyzed 3 weeks, 5 days ago
Protocol Compliance
Probed 3 weeks, 5 days ago
Add this to your README to display your MCP Scoreboard grade:
