Provides a command-line interface for interacting with MCP servers. Supports discovering configured servers, exploring available tools with parameter details, and invoking tools with type-safe arguments. Works with SSE, Streamable HTTP, and stdio transports. Auto-detects and merges configuration from standard locations.
Cognium trust score
85%
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.