---
title: A2A Traffic Gateway
description: Observe Agent-to-Agent (A2A) protocol traffic through AI Gateway.
url: "/ai-gateway/a2a/"
canonical_url: "/ai-gateway/a2a/"
content_type: landing_page
products:
- AI Gateway
tags:
- ai
- a2a
canonical: true


---






# Observability and control layer for Agent-to-Agent protocol traffic

Route A2A traffic through AI Gateway with protocol-aware metrics, tracing, and agent card rewriting
## Route A2A traffic through AI Gateway

The [Agent-to-Agent (A2A)](https://a2aproject.github.io/A2A/) protocol defines how AI agents communicate with each other over HTTP using JSON-RPC and REST bindings. As agent-to-agent communication moves into production, teams need visibility into A2A traffic and control over how it flows.

AI Gateway acts as a control and observability layer for A2A traffic, enabling you to route agent-to-agent requests, extract task metadata, and rewrite agent card URLs so clients route through the Gateway.
This gives you a single point of control over how agents discover and call each other, with structured metrics fed into the Konnect analytics pipeline.
Configure A2A traffic using [AI Agents](/ai-gateway/entities/ai-agent/) and attach [AI Policies](/ai-gateway/entities/ai-policy/) for authentication, access control, and observability.


![Overview of A2A traffic flowing through AI Gateway](/assets/images/ai-gateway/a2a.svg)



## Proxy and observe A2A traffic
Create an [AI Agent](/ai-gateway/entities/ai-agent/) entity to proxy A2A traffic, then attach an OpenTelemetry [AI Policy](/ai-gateway/entities/ai-policy/) to export traces and metrics for that traffic.




## Secure A2A endpoints
Reference an AI Auth Strategy on your AI Agent entities to authenticate A2A clients, and attach the Request Size Limiting Policy to limit request size before traffic reaches your agents.





## Create and monitor an AI Agent

Set up an AI Agent to proxy A2A traffic and observe it with OpenTelemetry.



* [AI Agent entity](/ai-gateway/entities/ai-agent/)

* [Get started with AI Agent](/ai-gateway/get-started-with-ai-agent/)

* [Monitor AI Agent traffic with OpenTelemetry](/ai-gateway/monitor-ai-agent-with-opentelemetry/)



## Secure A2A endpoints

Apply AI Policies to authenticate clients and limit request size for A2A traffic.


* [AI Auth Strategy entity](/ai-gateway/entities/ai-auth-strategy/)

* [Set up a Kong Identity auth server for AI Agent authentication](/ai-gateway/set-up-kong-identity-for-a2a/)

* [Secure AI Agent traffic with OpenID Connect and Kong Identity](/ai-gateway/secure-ai-agent-with-oidc/)

* [Request Size Limiting policy](/ai-gateway/policies/request-size-limiting/)

* [Limit request body size](/ai-gateway/limit-a2a-body-size/)



## Observe A2A traffic

AI Gateway records A2A protocol traffic data so you can analyze how agent-to-agent requests are processed and resolved.
- Audit logs capture task IDs, JSON-RPC method calls, payloads, latencies, and errors.
- OpenTelemetry spans record task state, context IDs, TTFB, SSE event counts, and response sizes.
- Metrics track A2A-specific signals and performance indicators over time.


### A2A audit logs

Review AI A2A Proxy log output fields, task states, and payload capture.




### A2A OpenTelemetry spans

Inspect A2A-specific span attributes in distributed traces.




### A2A OpenTelemetry metrics

Monitor A2A-specific OTLP metrics and telemetry signals.




### Agentic usage analytics in Konnect

View A2A-specific metrics and analytics in Konnect.




## Manage A2A traffic

AI Gateway records A2A protocol traffic data so you can apply rate limits, authenticate users, and restrict request types.


### Rate limit A2A traffic

Apply rate limits to A2A routes proxied through AI Gateway