The safeguards map / 3.3 Gateways
Prisma AIRS 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 commercial gateway (formerly Portkey) that proxies model and Model Context Protocol (MCP) traffic, with guardrail checks, tool provisioning and webhook guardrails that call out to an operator's own service.
Where it sits
3.3 Gateways (primary): Sits on the request path between applications and their models, and between MCP clients and MCP servers, and can deny a call when a guardrail check fails or a tool is not provisioned to the caller.
It acts as a proxy between MCP Clients and MCP servers, handling authentication, access control, and logging.
captured
Use Portkey’s Guardrails to verify your LLM inputs AND outputs, adhering to your specifed checks.
captured
Enable or disable specific tools per user when a server exposes tools that shouldn’t be available to everyone.
captured
Centralizes policy, access controls, and observability for LLM and AI service traffic
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
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.