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

Q: How do I connect the Kong (AI API Gateway) MCP Server to my LangChain setup?

Install the adapter using pip install langchain-mcp-adapters langgraph. Initialize the MultiServerMCPClient pointing to the server URL, pull the tools via gettools(), and pass them to your agent.

Q: Can my LangChain agent dynamically switch LLM models using Kong (AI API Gateway)?

Yes, your agent can call updateplugin to modify the AI Proxy configuration on any active service. This lets you swap model backends or adjust rate limits programmatically based on real-time chain performance.

Q: Does the Kong (AI API Gateway) MCP Server expose my API keys and consumer secrets?

No, sensitive data like credentials generated by createconsumerkey are handled within an isolated V8 sandbox on Vinkius. Only the direct API responses necessary for routing are returned to your agent, keeping your gateway admin tokens completely secure.

Run your Kong (AI API Gateway) routing and plugin deployments directly inside LangChain chains and ReAct agent loops.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Kong services dynamically via LangChain

Deploy new backend endpoints on the fly by letting your ReAct agent execute `create_service`. When a new backend comes online, the agent registers it and immediately links an external path to it using `create_route`. You don't have to write manual glue code or run shell scripts anymore. Because LangChain tracks every tool execution in LangSmith, you can audit exactly when and why your agent updated your gateway configuration. You get full visibility into the exact inputs and outputs of every single gateway modification.

Automate AI gateway security in your agent loops

Apply instant authentication rules to your routes by calling `create_consumer_key` directly from your agent. When a new user signs up, the agent triggers the tool to generate their gateway credentials. It then couples this key with the upstream LLM provider by configuring the `create_ai_plugin` tool on their dedicated route. This setup turns your Kong gateway into a self-configuring proxy. If a tenant starts hitting rate limits, your LangChain chain detects the trend and fires off `update_plugin` to swap models or adjust thresholds without manual intervention.

Inspect gateway state inside multi-step chains

Inspect your current routing topology using `list_services` to build self-healing infrastructure pipelines. Your chain can run this and `list_routes` to map out the active paths. If a route is missing or misconfigured, the agent automatically fixes it in the next step of the chain. This MCP Server exposes the raw state of your gateway to your agent's reasoning loop. By calling `list_plugins` and cross-referencing it with active routes, the agent ensures your traffic policies are active before routing live production calls.

Setup guide

Set up Kong (AI API Gateway) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kong (AI API Gateway) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kong-ai-api-gateway-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kong (AI API Gateway) transactions"
    })
    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 LangChain

Install the adapter using `pip install langchain-mcp-adapters langgraph`. Initialize the `MultiServerMCPClient` pointing to the server URL, pull the tools via `get_tools()`, and pass them to your agent.

Yes, your agent can call `update_plugin` to modify the AI Proxy configuration on any active service. This lets you swap model backends or adjust rate limits programmatically based on real-time chain performance.

LangSmith captures every single parameter sent to tools like `create_route` or `create_service`. You can trace exactly what configurations were sent, view latency metrics, and debug failed gateway updates instantly.

Yes, you can spin up multiple server instances pointing to different gateway admin endpoints. Your agent can then coordinate changes across staging and production environments within a single execution block.

No, sensitive data like credentials generated by `create_consumer_key` are handled within an isolated V8 sandbox on Vinkius. Only the direct API responses necessary for routing are returned to your agent, keeping your gateway admin tokens completely secure.

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