The safeguards map / 3.3 Gateways
Google Apigee AI gateway and MCP
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
The AI gateway and Model Context Protocol (MCP) features of Apigee: model and MCP tool call governance with OAuth, Model Armor filtering and token limits, with OpenTelemetry trace export.
Where it sits
3.3 Gateways (primary): Sits in front of large language model (LLM) and MCP traffic and applies Apigee policies, including OAuth authentication on MCP proxies and Model Armor prompt filtering.
Apigee provides AI gateway related features to govern and optimize your AI traffic
captured
Apply Apigee policies to traffic that is not fronted by an Apigee proxy, including an AI agent's model and MCP tool calls.
captured
Add an OAuth V2 security policy to ensure all requests to your MCP proxy are authenticated and authorized.
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 settings
- Traffic it sees
- model callstool calls (MCP)
- Can the agent bypass it
- depends
Handoffs
produces Runtime records: OpenTelemetry trace export
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.