How to Use the Kong (AI API Gateway) MCP in AutoGen

Q: How do I load the Kong (AI API Gateway) MCP Server into my AutoGen agents?

Use pip install -U autogen-extmcp to get the extension. Initialize the server tools using the MCP extension parameters and pass the tool list directly to your AssistantAgent constructor.

Q: Does this MCP integration support multi-agent parallel execution?

Yes, different agents can call tools like listservices and listconsumers simultaneously to gather gateway state, speed up analysis, and feed the data back into their decision-making loop.

Let your AutoGen agents debate and coordinate gateway routing, security plugins, and rate-limiting rules.

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 AutoGen

Create your Vinkius account to connect Kong (AI API Gateway) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven gateway deployments with AutoGen

Coordinate multi-agent gateway deployments by letting one agent run `create_service` while another validates it. A developer agent can propose a routing change, while a dedicated security agent reviews the configuration and triggers `create_ai_plugin` to enforce authentication before the route goes live. This multi-agent framework ensures that no single agent can modify your gateway without peer review. They debate the changes in a conversation loop, converging on the safest configuration before executing any API calls.

Coordinate dynamic rate-limiting and model failovers

Manage traffic spikes dynamically by letting your agents execute `update_plugin` to adjust rate limits. When a performance agent flags high latency, a coordinator agent can invoke the tool to swap the underlying LLM provider or tighten rate limits on specific consumers found via `list_consumers`. By separating concerns between different specialized agents, you avoid single-point-of-failure logic. One agent monitors, one analyzes, and the other executes the gateway updates, keeping your system highly resilient.

Clean up deprecated configurations safely using an MCP Server

Verify active endpoints with `list_routes` before allowing your agents to clean up deprecated configurations. A clean-up agent can run this to identify inactive endpoints, while a compliance agent checks `list_plugins` to verify no active security policies are bypassed before calling `delete_plugin`. This collaborative approach prevents accidental downtime. The agents must agree that a service is completely safe to delete before executing the final API calls, ensuring high reliability for your production gateway.

Setup guide

Set up Kong (AI API Gateway) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kong (AI API Gateway) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kong (AI API Gateway)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kong (AI API Gateway) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kong (AI API Gateway)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kong (AI API Gateway) data")
    print(result.messages[-1].content)

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 AutoGen

Use `pip install -U autogen-ext[mcp]` to get the extension. Initialize the server tools using the MCP extension parameters and pass the tool list directly to your `AssistantAgent` constructor.

Yes, you can set up a security agent and a platform agent that discuss the parameters of `create_ai_plugin` before executing it. This ensures all gateway plugins meet your compliance standards.

The agents use conversational consensus to resolve conflicts. If one agent tries to run `create_route` on an existing path, another agent checking `list_routes` will flag the conflict and suggest a different path.

Yes, different agents can call tools like `list_services` and `list_consumers` simultaneously to gather gateway state, speed up analysis, and feed the data back into their decision-making loop.

The server runs inside an isolated, zero-trust V8 sandbox on Vinkius. Key generation via `create_consumer_key` is processed entirely within this secure runtime, preventing raw credentials from leaking into the agents' conversation histories.

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