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

Q: How do I integrate Kong (AI API Gateway) with Google ADK?

Run pip install google-adk. Create an McpToolset pointing to your HTTP or Stdio transport URL. Pass that toolset directly to your LlmAgent configuration.

Q: Can Google ADK restrict which Kong (AI API Gateway) tools the agent uses?

You apply a toolnames filter when setting up the MCP McpToolset. This prevents the agent from calling destructive actions like deleteplugin in production environments.

Q: How does Kong (AI API Gateway) manage API keys for Gemini?

You configure the gateway using createaiplugin to inject your provider keys at the proxy layer. Your client apps hit the Kong route without ever knowing the actual LLM credentials.

Q: What happens if I need to change model providers under heavy load?

The agent executes updateplugin on the fly. It modifies the ai-proxy target to shift traffic from one model to another instantly, bypassing the need for application redeployments.

Build Gemini-powered infrastructure managers that control Kong (AI API Gateway) through Google ADK.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic AI Proxy Routing

Calling `create_service` establishes a new backend target in Kong via the MCP Server. Your Gemini agent then pairs this with `create_route` to expose the endpoint to your internal network. You secure that route by executing `create_ai_plugin`. This attaches the `ai-proxy` logic directly to the path, handling model routing and key management at the edge rather than inside your Google Cloud application.

Manage Google ADK Consumers

The `create_consumer_key` tool provisions API credentials for new users interacting with your system. Your agent handles this automatically when onboarding new accounts. To see who has access, the agent runs `list_consumers`. It parses the active profiles and can revoke access or adjust quotas using `update_plugin` if it detects unusual traffic patterns.

Audit the MCP Server Configuration

Executing `list_services` and `list_routes` extracts the entire gateway topology into Gemini's massive context window. The agent analyzes the map to find orphaned endpoints or missing security policies. When it finds outdated rules, the agent takes action. It triggers `delete_plugin` to remove legacy rate limits or authentication blocks that no longer apply to your current architecture.

Setup guide

Set up Kong (AI API Gateway) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Kong (AI API Gateway) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Kong (AI API Gateway)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kong (AI API Gateway) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk`. Create an `McpToolset` pointing to your HTTP or Stdio transport URL. Pass that toolset directly to your `LlmAgent` configuration.

You apply a `tool_names` filter when setting up the MCP `McpToolset`. This prevents the agent from calling destructive actions like `delete_plugin` in production environments.

You configure the gateway using `create_ai_plugin` to inject your provider keys at the proxy layer. Your client apps hit the Kong route without ever knowing the actual LLM credentials.

The agent executes `update_plugin` on the fly. It modifies the `ai-proxy` target to shift traffic from one model to another instantly, bypassing the need for application redeployments.

This MCP Server integration strictly reads and writes gateway configuration payloads like routing URLs and consumer credentials. Google ADK transmits these commands through an authenticated, single-endpoint token system. We destroy the execution environment immediately after the request completes.

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