The safeguards map / 3.3 Gateways
Traefik Hub AI Gateway
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
A proprietary API gateway layer for large language model (LLM) and Model Context Protocol (MCP) traffic with content guard middleware, task-based tool access rules and delegation of decisions to an external policy engine.
Where it sits
3.3 Gateways (primary): Sits on the route between clients and model providers or MCP servers, runs content guard rules on requests and responses and can send MCP tool-call decisions to an external policy engine.
The AI Gateway adds a thin, dedicated control layer on top of Traefik Hub’s API Gateway.
captured
Run Content Guard rules on requests and responses before they reach the model.
captured
The AuthZEN MCP middleware that sends MCP Gateway tool-call decisions to an external policy engine.
captured
Fine-grained authorization across three dimensions
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agentAI system
- Used by
- those who run it
- Runs
- at runtime
- Policy comes from
- owner-entered settingsan external decision point
- Traffic it sees
- model callstool calls (MCP)
- Can the agent bypass it
- depends
Handoffs
produces Runtime records: OpenTelemetry-compatible metrics and traces
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.