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

Q: How do I connect Kong (AI API Gateway) to the Vercel AI SDK?

Pass the Vinkius endpoint URL into createMCPClient({ transport: { type: "http", url: "..." } }). Call mcpClient.tools() and feed the results into streamText to let your MCP client manage the gateway.

Q: Can the Vercel AI SDK handle Kong (AI API Gateway) auth creation?

Yes. Your agent calls createconsumerkey and streams the resulting API key directly to your frontend component. You handle the UI state while the SDK manages the tool execution.

Q: How does this MCP server list active configurations?

It uses listservices and listconsumers to pull the active registry. The agent reads these lists to understand the current architecture before making changes.

Stream Kong API gateway configurations directly into your React frontend with the 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 (AI API Gateway) MCP to Vercel AI SDK

Create your Vinkius account to connect Kong (AI API 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 (AI API Gateway) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Configure upstream routes live in Vercel AI SDK

The `create_service` tool binds a new backend service to your Kong gateway. When your user asks to add a new LLM provider, your Vercel AI SDK MCP agent executes this call and streams the confirmation straight to the UI. You don't have to wait for a background job to finish. The agent immediately calls `create_route` to expose that service on a specific path, rendering the new endpoint details in your Next.js dashboard as they are created.

Apply AI proxy rules dynamically

Your agent uses `create_ai_plugin` to attach the ai-proxy behavior to specific routes. If a user needs to switch from one model provider to another, the agent handles the plugin configuration on the fly. When traffic spikes, the agent can stream the execution of `update_plugin` to adjust rate limits. The user watches the configuration update in their browser without a page refresh.

Audit gateway state via this MCP Server

Reading the current gateway state starts with the `list_plugins` and `list_routes` tools. Your agent pulls the active routing rules and enabled plugins, pushing the raw JSON data into a formatted Svelte or React table. It handles access control just as fast. The agent runs `create_consumer_key` to generate API credentials, displaying the new token in the frontend immediately so the user can copy it.

Setup guide

Set up Kong (AI API 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 (AI API 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 (AI API 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. 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 Vercel AI SDK

Pass the Vinkius endpoint URL into `createMCPClient({ transport: { type: "http", url: "..." } })`. Call `mcpClient.tools()` and feed the results into `streamText` to let your MCP client manage the gateway.

Yes. Your agent calls `create_consumer_key` and streams the resulting API key directly to your frontend component. You handle the UI state while the SDK manages the tool execution.

The tool call returns an error payload. The SDK surfaces this exception in the stream, allowing your React error boundaries to catch and display the gateway failure.

It uses `list_services` and `list_consumers` to pull the active registry. The agent reads these lists to understand the current architecture before making changes.

No. The server only transmits configuration metadata like route paths, service names, and consumer IDs. It never intercepts the actual payload content flowing through your API endpoints, operating entirely inside an ephemeral V8 sandbox.

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