How to Use the Traefik Hub MCP in Vercel AI SDK

Q: How do I check API metrics using Traefik Hub with Vercel AI SDK?

You call traefikgetapimetrics and stream the resulting structured telemetry. This allows your Vercel frontend to display real-time error traces and latency data right next to the streamed text, giving developers crucial diagnostic information instantly.

Q: What if I need to revoke a user's token using Traefik Hub with Vercel AI SDK?

Use traefikrevokesubscription to ban and completely tear down an active API consumer token. Your agent executes this, and you can confirm the revocation status in your streaming UI, providing immediate feedback to both the user and yourself.

Q: Does Traefik Hub help with listing available scopes for Vercel AI SDK?

Yes, run traefiklistworkspaces to enumerate active logic scopes. This lets your client build out a selector UI that accurately reflects the namespaces and API Portals currently configured in Traefik Hub.

Q: Can I view all connected agents with Traefik Hub for Vercel AI SDK?

Absolutely. Call traefiklistactiveagents to locate every explicitly hosted Traefik Ingress deployment pod mapped dynamically onto the hub. This list is essential for verifying your application's overall backend connectivity before any data streams.

Real-time API Gateway data streams directly into your Next.js 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 Traefik Hub MCP to Vercel AI SDK

Create your Vinkius account to connect Traefik Hub 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 Traefik Hub with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

View all published APIs

The `traefik_list_apis` tool dumps the central directory of every internal and external HTTP API routing across your Gateway. When you call this, your agent gets a complete map of endpoints, letting you build client-side logic that knows exactly what data is available to stream into the UI. It's perfect for setting up initial state checks. You can run this before streaming content, so the user sees not only the AI response but also confirmation that all necessary backend services are reachable.

Monitor agent health status

Need to know if your connected microservices are actually up? `traefik_get_agent_health` evaluates operational execution limits by testing liveness probes across ingress hubs. Your AI client can check this, giving you a real-time health score that displays immediately in the frontend. If an agent fails its probe, you don't just get an error message; your UI updates to show exactly which service is down and why, keeping the user informed while the streaming content pauses.

Manage user access tokens

Security is key. The `traefik_list_subscriptions` tool maps explicitly tracked external identities that are trying to gain logic access over proxy portals. You can use this list to validate permissions before allowing data to stream, preventing unauthorized calls from hitting your backend. When a user tries to access something they shouldn't, your agent sees the attempt and reports it back instantly, letting you display a precise error message in the client UI instead of just failing silently.

Setup guide

Set up Traefik Hub 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 Traefik Hub 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 Traefik Hub 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 Traefik Hub. 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 Traefik Hub 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 Traefik Hub MCP in Vercel AI SDK

You call `traefik_get_api_metrics` and stream the resulting structured telemetry. This allows your Vercel frontend to display real-time error traces and latency data right next to the streamed text, giving developers crucial diagnostic information instantly.

Use `traefik_revoke_subscription` to ban and completely tear down an active API consumer token. Your agent executes this, and you can confirm the revocation status in your streaming UI, providing immediate feedback to both the user and yourself.

Yes, run `traefik_list_workspaces` to enumerate active logic scopes. This lets your client build out a selector UI that accurately reflects the namespaces and API Portals currently configured in Traefik Hub.

Absolutely. Call `traefik_list_active_agents` to locate every explicitly hosted Traefik Ingress deployment pod mapped dynamically onto the hub. This list is essential for verifying your application's overall backend connectivity before any data streams.

This server touches API consumer tokens and identity subscription information. You can use `traefik_list_subscriptions` to map which external identities are attempting access, allowing you to build robust permission checks into your client-side logic.

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