A security scanner that evaluates installed MCP servers for vulnerabilities by aggregating findings from 16 scanning engines into detailed trust scores. It enables users to scan their local AI agent configurations or specific repository URLs for potential security risks.
Security scanner and trust verification layer for MCP ecosystem, enabling users to scan PyPI packages and GitHub repos for secrets, dangerous patterns, and prompt injection vectors, and compare security scores.
Scans MCP tool descriptions for prompt injection attacks, including cross-tool instructions, privilege escalation, and data exfiltration patterns. It can be used as a CLI scanner or integrated as an MCP server itself.
