Topic starter
24/06/2026 7:24 pm
TL;DR: AI policy now has to follow the full request path, not just the application perimeter, as Kong AI Gateway 3.14 adds native agent-to-agent traffic control, token exchange, scope-based tool filtering, and JWK validation to govern multi-agent AI workflows without code changes, according to Kong.
Editorial analysis by NHI Mgmt Group, based on content published by Kong: “# Govern the Full AI Data Path with Kong AI Gateway 3.14”.
Key questions
Q: How should security teams govern agent-to-agent traffic in AI workflows?
A: Security teams should treat agent-to-agent traffic as a governed identity path, not as ordinary internal API chatter.
Q: Why do token exchange and downscoping matter for AI agents?
A: They matter because an upstream token should not automatically retain broad authority as it moves through a chain of agents and tools.
Q: What breaks when tool permissions are managed only in application code?
A: When tool permissions live only in application code, teams lose a central enforcement point and policy quickly becomes inconsistent across workflows.
Practitioner guidance
- Define gateway-level policy for A2A traffic Place authentication, rate limiting, and logging at the layer that sees agent-to-agent calls, not only client-to-agent requests.
- Downscope delegated tokens before forwarding Use token exchange to reduce upstream authority to the minimum audience and scopes needed for the next service or agent.
- Map OAuth2 scopes to tool permissions Tie tool access to scopes so read-only and write-capable agents are separated at the gateway.
Bottom line: Multi-agent AI workflows now need governance at the request path because policy embedded only in application code cannot keep pace with every hop.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 4:41 am
The AI gateway is becoming the control plane for delegated identity in agentic systems. Once agent-to-agent traffic is part of production workflows, the decision about who can do what moves out of application code and into the request path. That changes governance from a developer-by-developer problem to a platform-enforced one, which is exactly where identity policy belongs when agents are composing actions across services.
A few things that frame the scale:
- 71% of organizations use third-party APIs, according to Gartner’s 2024 data.
A question worth separating out:
Q: How do teams handle JWK-only token validation for MCP traffic?
A: They should validate tokens at the gateway using published JWKs, cache keys safely, and continue to check audience and scope on every request. That approach supports identity providers that do not expose introspection while keeping the control point centralised. The main governance task is to ensure the validation model stays consistent across providers.
👉 Read our full editorial: Kong AI Gateway 3.14 shifts control to the AI data path