"Gcore" matching MCP servers:

Enables an agent or MCP client to scan MCP server configs and AI-agent tool manifests on demand, exposing tools that list detection rules and report hidden prompt injections, data-exfiltration attempts, embedded secrets, deceptive Unicode, unpinned packages and shell-launching tools. Each finding comes with a severity and location so risky tool descriptions can be caught before an attacker exploits them.

A model-neutral cyber capability brain for AI agents and human researchers, providing MCP tools for knowledge ingestion, composition, campaign planning, fleet management, evidence binding, and discovery replay.