Map / MCP & LLM Gateways / aggrete

aggrete

United States · Founded 2026

Quick answer: aggrete is an AI security company based in the United States and founded in 2026, working in MCP & LLM Gateways and Observability & Governance.

MCP & LLM GatewaysObservability & Governance

Capabilities

Open-source MCP proxy sitting as a governance layer between AI assistants/agents and backend data connectors (Slack, GitHub, Drive, Jira, Salesforce, Notion), enforcing a YAML-defined policy on every tool call.

Sensors / integration

Intercepts every tool call before it reaches the upstream system, accumulates per-user activity/state with TTL-based memory across calls and sessions, and inspects inbound/outbound content for secrets and PII.

Protections

Blocks requests that would leak a secret, cross an information barrier, over-share sensitive data, complete a forbidden combination of actions, or write out after reading untrusted content; also targets prompt injection, rug-pull attacks, and tool poisoning, with tamper-evident audit logging.

Differentiator

Deterministic, non-ML policy enforcement that reasons over accumulated per-user, cross-call/session context to catch multi-step violations that point-in-time scanners miss; fully open-source and self-hostable in front of existing connectors.

Team & funding

Founders
Christian Johannsen

Other MCP & LLM Gateways companies

Acuvity · Aembit · agen.co · Agentic Fabriq · AI Aramid · AI Security Gateway · Aim Security · AIR · aizome · Akeyless Security · AptaSentry · Aptible · See all →

Last updated · Get the “Listed on” badge