—
/100
Partial
○ Unscored 1⁄3
Cursor Agent Poisoning
A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.
Glama
Unscored visibility
— 1/3 applicable dimensions scored
○ Schema Quality
— Protocol
— Reliability
○ Docs & Maintenance
✓ Security Hygiene
— Schema Interpretability
Schema Quality
—
42% weight
Protocol Compliance
N/A
Local server
Reliability
N/A
Local server
Docs & Maintenance
—
25% weight
Security Hygiene
95
33% weight
Score History
Category Trends
Add this to your README to display your MCP Scoreboard grade:
