—
/100
Partial
○ Unscored 1⁄4
threadline
Persistent memory and context layer for AI agents. inject() before your LLM call, update() after. Relevance-scored injection, grant-based access control, user-owned context. Works with OpenAI, Anthropic, Vercel AI SDK, and LangChain. < 50ms retrieval. GDPR-ready. Free tier: 2,500 calls/month.
Anthropic
LangChain
OpenAI
Vercel
Smithery
Unscored visibility
— 1/4 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
—
25% weight
Protocol Compliance
—
20% weight
Reliability
—
20% weight
Docs & Maintenance
—
15% weight
Security Hygiene
81
20% weight
Score History
Category Trends
30-Day Uptime
30 days ago
Today
Add this to your README to display your MCP Scoreboard grade:
