—
/100
Unscored
○ Unscored 0⁄0
mcp-llm-eval
A local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.
Glama
Unscored visibility
— 0/0 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
—
20% weight
30-Day Uptime
30 days ago
Today
Add this to your README to display your MCP Scoreboard grade:
