This MCP proxy gateway consolidates multiple upstream MCP servers behind a single interface using schema deferral to reduce token overhead and response shielding to prevent context overflow. Instead of loading all upstream tool schemas at startup, clients see only six gateway tools: search (BM25), describe, invoke, async invoke, status, and paginated result retrieval. It runs as an HTTP daemon serving multiple AI clients simultaneously, eliminating redundant server processes.
Cognium trust score
63%
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.