Production-oriented MCP server wrapper around LLAMATOR for automated LLM red teaming and security testing. Provides both HTTP API and MCP tool interfaces for submitting asynchronous test runs against OpenAI-compatible endpoints, with execution orchestrated via ARQ/Redis and artifacts stored in MinIO with presigned download URLs. Features API key protection, request persistence with secret redaction, Prometheus metrics, and comprehensive job lifecycle management including status tracking and error handling.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.