87
/100
A
◉ Complete 5⁄5
cortexgraph
Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.
Glama
MCP Surface
Tools: 17
Schema Drift
Complete visibility
— 5/5 applicable dimensions scored
✓ Schema Quality
✓ Protocol
— Reliability
✓ Docs & Maintenance
✓ Security Hygiene
✓ Schema Interpretability
Schema Quality
84
42% weight
Protocol Compliance
N/A
Local server
Reliability
N/A
Local server
Docs & Maintenance
88
25% weight
Security Hygiene
95
33% weight
Schema Interpretability
86
15% weight
Score History
Category Trends
Static Analysis
| Metric | Score | Rating |
|---|---|---|
| Schema Completeness | 80 | Good |
| Description Quality | 90 | Good |
| Documentation Coverage | 90 | Good |
| Maintenance Pulse | 74 | Good |
| Dependency Health | 100 | Good |
| License Clarity | 100 | Good |
| Version Hygiene | 90 | Good |
Analyzed 1 month ago
Protocol Compliance
Schema Issues (70)
analyze_for_recall.message: missing description
analyze_message.message: missing description
auto_recall_process_message.message: missing description
backfill_embeddings.model: missing description
backfill_embeddings.limit: missing description
backfill_embeddings.force: missing description
backfill_embeddings.dry_run: missing description
cluster_memories.strategy: missing description
cluster_memories.threshold: missing description
cluster_memories.max_cluster_size: missing description
cluster_memories.find_duplicates: missing description
cluster_memories.duplicate_threshold: missing description
consolidate_memories.cluster_id: missing description
consolidate_memories.mode: missing description
consolidate_memories.auto_detect: missing description
... and 55 more
Probed 1 month ago
Add this to your README to display your MCP Scoreboard grade:
