Kong (AI API Gateway) MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Kong (AI API Gateway) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Kong (AI API Gateway) Assistant",
instructions=(
"You help users interact with Kong (AI API Gateway). "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Kong (AI API Gateway)"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Kong (AI API Gateway) MCP Server
Connect your Kong API Gateway instance to any AI agent and take full control of your API lifecycle and AI traffic management through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from Kong (AI API Gateway) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Kong (AI API Gateway), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Service Orchestration — List backend services and create new upstream definitions defining URLs and protocols directly from your agent
- Route Management — Configure inbound routing rules to map client requests to backend services based on specific paths or hostnames
- AI Plugin Control — Apply and configure the
ai-proxyplugin to enable LLM routing, model providers, and key encapsulation securely - Operational Patching — Update existing plugin configurations in real-time, allowing you to adjust rate limits or swap AI models dynamically
- Consumer CRM — Manage consumer profiles and generate API keys for
key-authplugins to track specific user or tenant usage - Infrastructure Audit — Discover enabled plugins across your gateway and remove unused modules instantly to maintain a clean proxy pipeline
The Kong (AI API Gateway) MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Kong (AI API Gateway) to OpenAI Agents SDK via MCP
Follow these steps to integrate the Kong (AI API Gateway) MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Kong (AI API Gateway)
Why Use OpenAI Agents SDK with the Kong (AI API Gateway) MCP Server
OpenAI Agents SDK provides unique advantages when paired with Kong (AI API Gateway) through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Kong (AI API Gateway) + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Kong (AI API Gateway) MCP Server delivers measurable value.
Automated workflows: build agents that query Kong (AI API Gateway), process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Kong (AI API Gateway), another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Kong (AI API Gateway) tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Kong (AI API Gateway) to resolve tickets, look up records, and update statuses without human intervention
Kong (AI API Gateway) MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Kong (AI API Gateway) to OpenAI Agents SDK via MCP:
create_ai_plugin
Frequently used for enabling the `ai-proxy` plugin for LLM routing and key encapsulation. Apply a new Plugin (like AI Proxy) to a specific Service
create_consumer_key
Generate an API Key credential for a Kong Consumer
create_route
Create a new Route to expose a Service in Kong
create_service
The payload must define the upstream URL, name, and protocol information. Create a new backend Service in Kong
delete_plugin
Delete and permanently remove a Plugin from the Kong Gateway
list_consumers
List all Consumer profiles registered in Kong
list_plugins
g., Rate Limiting, AI Proxy, Key Auth) currently configured globally or scoped to specific Services/Routes. List all enabled Plugins on the Kong Gateway
list_routes
List all routing rules configured in the Kong API Gateway
list_services
List all Services registered in the Kong API Gateway
update_plugin
Useful for adjusting rate limits dynamically or swapping AI model providers under heavy load. Update the configuration of an existing Kong Plugin
Example Prompts for Kong (AI API Gateway) in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Kong (AI API Gateway) immediately.
"List all registered services in my Kong Gateway"
"Add the 'ai-proxy' plugin to service ID '123-abc' using OpenAI"
"Who are the registered consumers in our gateway?"
Troubleshooting Kong (AI API Gateway) MCP Server with OpenAI Agents SDK
Common issues when connecting Kong (AI API Gateway) to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Kong (AI API Gateway) + OpenAI Agents SDK FAQ
Common questions about integrating Kong (AI API Gateway) MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Kong (AI API Gateway) with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Kong (AI API Gateway) to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.