Reverse proxy that adds authorization controls between AI agents and MCP servers. Implements delegation chain validation via RFC 8693 JWT, a tool policy engine for permanent blocks and scope checks, and behavioral anomaly detection for unusual patterns. Requires zero code changes to existing setups.
Cognium trust score
81%
Tier
Verified
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.