How to Use the Kong Gateway MCP in AutoGen

Q: How does AutoGen handle conflicting goals when managing Kong Gateway?

Through conversation. If a PerformanceAgent wants to updateplugin to increase a rate limit, a FinanceAgent might check a cost model and argue against it. They negotiate a compromise that both agents agree on.

Q: Can I build a security audit team for my Kong Gateway with AutoGen?

Definitely. You can have one agent that uses listconsumers and another that uses listplugins to check for security issues. They can then collaborate on a report or even take corrective action using tools like deleteconsumer.

Let AutoGen agents debate and decide on the best way to manage your Kong Gateway. Turn API management into a collaborative, automated MCP process.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kong Gateway MCP to AutoGen

Create your Vinkius account to connect Kong 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 Gateway with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Gateway Changes

Don't just execute commands. Propose them. An `AppDevAgent` can suggest using `create_route` to expose a new feature. A `SecOpsAgent`, armed with the `list_plugins` tool, can review the proposal and argue that a security plugin must be added first. The agents converse, challenge each other, and reach a consensus before any changes are made. The final plan is better because it accounts for multiple perspectives, just like a real platform engineering team.

Specialized Agents, Shared MCP Server

Create a team of agents with different jobs. One agent's only role is to monitor upstream health using `list_targets` and `get_upstream`. If it detects a problem, it informs a `TrafficAgent`, which then decides whether to use `update_route` or `delete_target` to fix it. This separation of concerns makes your automation more reliable. Each agent uses a small, specific set of tools from the Kong Gateway MCP Server, reducing the chance of unintended side effects.

Simulate Changes Before Applying

Run a 'dry-run' conversation. The agents can debate the steps for a major migration—using `create_service`, `create_route`, and `update_upstream`—and output the final plan without actually calling the tools. You get a human-readable transcript of the debate and a final, validated sequence of operations. When you're ready, you can approve the plan and let the agents execute it for real.

Setup guide

Set up Kong 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 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 Gateway_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kong 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 Gateway_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kong 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 Gateway. 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 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 Gateway MCP in AutoGen

Yes, that's a perfect use case. A 'proposer' agent can formulate a plan using `create_service` and `create_route`, and an 'approver' agent can vet the plan against a set of rules before execution.

Through conversation. If a `PerformanceAgent` wants to `update_plugin` to increase a rate limit, a `FinanceAgent` might check a cost model and argue against it. They negotiate a compromise that both agents agree on.

Definitely. You can have one agent that uses `list_consumers` and another that uses `list_plugins` to check for security issues. They can then collaborate on a report or even take corrective action using tools like `delete_consumer`.

The MCP tool execution itself is fast, just like a direct API call. The time comes from the agent conversation, which is the point. You add a few seconds of deliberation to prevent hours of debugging a bad configuration push.

The data, which includes route paths, service names, and plugin configs, is passed between your agents as part of their conversation. This happens within the memory of your AutoGen application and the Vinkius sandbox, and is discarded once the session ends.

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