79
/100
B
◔ Limited 3⁄4
CPersona
Persistent AI memory server with 3-layer hybrid search (vector + FTS5 + keyword), confidence scoring via Reciprocal Rank Fusion, episodic/profile memory, and 16 tools. Zero LLM dependency. Works standalone with Claude Desktop and Claude Code. MIT licensed.
Anthropic
Glama
Limited visibility
— 3/4 applicable dimensions scored
✓ Schema Quality
○ Protocol
— Reliability
✓ Docs & Maintenance
✓ Security Hygiene
— Schema Interpretability
A remote probe is needed for Protocol and Reliability scores.
Schema Quality
92
25% weight
Protocol Compliance
—
20% weight
Reliability
—
20% weight
Docs & Maintenance
53
15% weight
Security Hygiene
81
20% weight
Score History
Category Trends
30-Day Uptime
30 days ago
Today
Static Analysis
| Metric | Score | Rating |
|---|---|---|
| Schema Completeness | 100 | Good |
| Description Quality | 80 | Good |
| Documentation Coverage | 47 | Fair |
| Maintenance Pulse | 75 | Good |
| Dependency Health | 50 | Fair |
| License Clarity | — | Poor |
| Version Hygiene | 90 | Good |
Analyzed 1 month, 1 week ago
Add this to your README to display your MCP Scoreboard grade:
