90
/100
A
◐ Assessed 3⁄3
recallnest
Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph with PPR traversal, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB + SQLite, zero external dependencies.
Anthropic
Google Gemini
SQLite
Glama
Assessed visibility
— 3/3 applicable dimensions scored
✓ Schema Quality
— Protocol
— Reliability
✓ Docs & Maintenance
✓ Security Hygiene
— Schema Interpretability
Schema Quality
90
42% weight
Protocol Compliance
N/A
Local server
Reliability
N/A
Local server
Docs & Maintenance
83
25% weight
Security Hygiene
95
33% weight
Score History
Category Trends
Static Analysis
| Metric | Score | Rating |
|---|---|---|
| Schema Completeness | 90 | Good |
| Description Quality | 90 | Good |
| Documentation Coverage | 62 | Fair |
| Maintenance Pulse | 83 | Good |
| Dependency Health | 75 | Good |
| License Clarity | 100 | Good |
| Version Hygiene | 90 | Good |
Analyzed 1 month, 2 weeks ago
Add this to your README to display your MCP Scoreboard grade:
