"author:a-polishchuk" matching MCP connectors:

Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes.

Verifies AI agent wallets, domains and manifests before any transaction. Returns TRUSTED/UNVERIFIED/SUSPICIOUS/BLOCK with full signal breakdown. Connected to EMA shared brain - bad actors flagged here are blocked network-wide instantly.

Real-time prompt injection and jailbreak detection for AI agents. Blocks instruction overrides, data exfiltration, tool poisoning and 8 attack types. Now with shared learning brain - confirmed attacks shared across the EMA network instantly. Grade A security for any AI pipeline.