K-Work Trust provides agent-readable pre-action gates for AI workflows operating on Korean business data. It evaluates vendor registration, payment release, and invoice operations against Korean business field logic, returning structured decisions with blocking issues, warnings, and recommended next actions. Exposes a Streamable HTTP remote MCP endpoint with low-quota test keys for public discovery.
Cognium trust score
64%
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 2026-09-01.
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.