An MCP server that enforces access control on internal knowledge, ensuring agents only retrieve and cite documents the caller is permitted to see, and refuses answers when permissions are insufficient.
Provides long-term memory for AI agents with per-user scoped recall, ranking by relevance, recency, and importance, consolidation of repeated events, and automatic forgetting.
A security gateway for MCP servers that enforces policy checks including role-based access, argument constraints, injection scanning, and PII redaction on both tool arguments and results, with tamper-evident audit logging.