How to Use the Kong Gateway MCP in Vercel AI SDK

Q: How do I connect Kong Gateway to my Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using createMCPClient with the Vinkius MCP endpoint. Pass the tools array directly into streamText or generateText to let your agent call tools like listservices or createroute. Always call mcpClient.close() once the request completes to free up connections.

Pipe real-time Kong Gateway routing updates directly to your frontend with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Kong Gateway to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live API routing updates with Vercel AI SDK

The `create_route` and `create_service` tools let your frontend app update your API gateway live. When your user requests a new endpoint, your app triggers these tools via the SDK's streaming text generation, building the backend mapping on the fly. You do not need to wait for a full deployment cycle or manual configuration steps. The Vercel AI SDK handles the tool calls inside Edge Functions, updating your gateway configuration in milliseconds and piping the success status straight to the user's interface.

Real-time consumer and credential provisioning

The `create_consumer` and `create_plugin` tools let you register users and attach key-auth or rate-limiting rules in one shot. Your agent runs these operations based on user input, configuring access controls instantly. Instead of staring at a blank loading screen, your users watch the credentials generate live on their screens. This MCP server handles the handshake, while the SDK handles the UI rendering to keep latency low.

Dynamic load balancing and target rotation

The `create_target` and `update_upstream` tools let your frontend control panel adjust traffic distribution on your backend. If a server goes down, your agent detects the issue and shifts the traffic weight. You do not need to write custom API clients or polling loops. The SDK calls the MCP server to inspect status and execute shifts, letting your team manage infrastructure directly from a web browser.

Setup guide

Set up Kong Gateway MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kong Gateway tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kong Gateway transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient` with the Vinkius MCP endpoint. Pass the tools array directly into `streamText` or `generateText` to let your agent call tools like `list_services` or `create_route`. Always call `mcpClient.close()` once the request completes to free up connections.

Yes, the server runs on Vinkius, meaning your Edge Functions only need to make a lightweight HTTP call. Your agent can execute tools like `get_status` and `list_plugins` within the Edge execution limits. This setup bypasses cold starts and keeps your gateway management fast.

The SDK reads the tool schemas directly from the MCP server, ensuring your agent sends the correct payload format. If the agent tries to call `update_service` with a bad URL, the validation error is caught before it hits your production admin API.

Yes, the SDK manages the connection lifecycle. You must invoke `mcpClient.close()` at the end of your serverless function execution. This prevents hanging TCP sockets between your Vercel deployment and the gateway.

Yes, Vinkius isolates all traffic and uses an ephemeral runtime to execute your tools. This server only handles your Kong Gateway admin credentials and API routing definitions. No raw application payload or user traffic passes through the Vinkius platform.

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