How to Use the Kong (AI API Gateway) MCP in OpenAI Agents SDK

Q: How do I connect Kong (AI API Gateway) to the OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Kong MCP server URL and pass it to your agent's mcpservers array. Set cacheToolsList=True to speed up tool discovery.

Q: Can the agent swap LLM providers during an outage?

Yes. The agent calls updateplugin to modify the ai-proxy configuration. This redirects traffic from a failing provider to a fallback model without changing your client-side code.

Q: How do I apply rate limits to specific routes?

Your agent runs listservices via the MCP integration to find the target upstream. It then uses createaiplugin to attach a rate limiting or AI proxy policy strictly to that service's associated route.

Manage your API gateways and LLM proxy routes safely using Kong with the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kong (AI API Gateway) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kong (AI API Gateway) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kong (AI API Gateway) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route LLM Traffic via MCP Server

Your agent uses `create_service` and `create_route` to spin up new backend endpoints on the fly. This maps your production OpenAI Agents SDK traffic through the Kong gateway instead of hitting provider APIs directly. You configure the `create_ai_plugin` tool to attach the `ai-proxy` behavior. This encapsulates your API keys at the gateway level, keeping them out of your application code and agent memory.

Enforce Consumer Limits

The `create_consumer_key` tool on this MCP Server generates access credentials for specific downstream clients. Your agent issues these keys dynamically when provisioning new tenant workspaces. You track usage by calling `list_consumers`. If a tenant abuses the system, the agent invokes `update_plugin` to throttle their specific route without affecting the rest of your user base.

Audit Gateway State

Calling `list_plugins` and `list_routes` gives your agent a complete map of the current traffic rules. It pulls this data to verify that rate limiting and AI proxy configurations match your desired state. When an endpoint is deprecated, the agent cleans up the mess. It fires `delete_plugin` to strip old configurations before dropping the upstream service entirely.

Setup guide

Set up Kong (AI API Gateway) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kong (AI API Gateway) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kong (AI API Gateway) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kong (AI API Gateway) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kong (AI API Gateway) Agent",
            instructions="You have access to Kong (AI API Gateway) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kong. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kong (AI API Gateway) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kong (AI API Gateway) MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Kong MCP server URL and pass it to your agent's `mcp_servers` array. Set `cacheToolsList=True` to speed up tool discovery.

Yes. The agent calls `update_plugin` to modify the `ai-proxy` configuration. This redirects traffic from a failing provider to a fallback model without changing your client-side code.

The SDK handles agent-level tracing natively. Your gateway handles network-level telemetry. Combining them gives you complete visibility from the agent's thought process down to the network request latency.

Your agent runs `list_services` via the MCP integration to find the target upstream. It then uses `create_ai_plugin` to attach a rate limiting or AI proxy policy strictly to that service's associated route.

The server handles routing configurations, API endpoint definitions, and consumer keys. Your OpenAI Agents SDK instance sends these administrative commands through a zero-trust V8 Isolate Sandbox. The connection is ephemeral and holds no persistent state.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript