Connects AI assistants to the Invariance observability platform, enabling natural language queries of traces, monitors, and signals to investigate issues and analyze agent behavior. Supports debugging, monitoring, and evaluation dataset management through Claude Desktop, Cursor, and Claude Code.
Cognium trust score
83%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
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.