The safeguards map / 3.3 Gateways
Praxis
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 proxy for AI infrastructure that routes model requests, aggregates Model Context Protocol (MCP) tools behind one endpoint, and applies rate limiting, auth and guardrails in a YAML-configured pipeline.
Where it sits
3.3 Gateways (primary): Sits between applications and AI providers and MCP servers, and applies rate limiting, authentication and guardrail filters that the deployer arranges in a YAML pipeline.
Send requests to OpenAI, Anthropic, or your own models.
captured
Native MCP gateway — aggregate tools from multiple servers behind one endpoint.
captured
How the AI gateway classifies requests, routes to providers, injects credentials, and speaks MCP and A2A.
captured
rate limiting, auth, guardrails, and routing in any order using a simple YAML config.
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)agent to agent (A2A)
- Can the agent bypass it
- depends
Handoffs
None recorded. A mapped entry with no handoff is here for its foundation home.
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.