How to Use the zrok (Open-Source Tunnel) MCP in Vercel AI SDK

Q: What tools can I use to list active tunnels with zrok (Open-Source Tunnel) and Vercel AI SDK?

You'll mainly use listshares and getshare. These tools let your agent check all currently running public or private shares. The results stream back, letting you show the user exactly what tunnels are active right now.

Q: Can I manage zrok (Open-Source Tunnel) environments in a multi-step flow with Vercel AI SDK?

Absolutely. You can chain calls like listenvironments followed by enableenvironment. Because the results stream, you'll see the environment list and the subsequent enabling status appear sequentially on the UI.

Q: If my user needs to delete a share using zrok (Open-Source Tunnel) with Vercel AI SDK, how is it handled?

The agent calls deleteshare and streams the confirmation back. This confirms to the user that the specific tunnel has been successfully terminated and removed from service.

Get real-time tunnel data into your UI 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 zrok (Open-Source Tunnel) MCP to Vercel AI SDK

Create your Vinkius account to connect zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Tunnels from Your Frontend

The `zrok (Open-Source Tunnel)` MCP Server exposes tools like `list_shares` and `get_share`. You can call these methods to fetch current tunnel status, allowing you to display live data in your React or Next.js components. Instead of waiting for a background job, the tool results stream directly into the user interface. Your agent reads the share details and displays them instantly—no loading spinner required.

Handle Authentication Live

When your application needs to secure access, use `zrok (Open-Source Tunnel)`'s `login_account` tool. This authenticates the session by providing a token that you pass through your streaming response. This means the user sees the account details and usage limits appear in real time as the agent executes the call. It keeps the entire process visible to the end user, making the AI interaction feel immediate and live.

Monitor Environment Status

Your app can check which environments are active using `list_environments`. You simply pass this tool result into your streaming response, showing users exactly what resources are currently enabled. If an environment needs to go down, you call `disable_environment` and stream the confirmation. The user sees the state change immediately in the UI, making it clear what's running and what isn't.

Setup guide

Set up zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) 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 zrok. 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 zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) MCP in Vercel AI SDK

This server touches account authentication details, specifically the endpoint token. Your agent uses this token to manage access without needing to expose sensitive credentials directly in the client code.

You'll mainly use `list_shares` and `get_share`. These tools let your agent check all currently running public or private shares. The results stream back, letting you show the user exactly what tunnels are active right now.

Absolutely. You can chain calls like `list_environments` followed by `enable_environment`. Because the results stream, you'll see the environment list and the subsequent enabling status appear sequentially on the UI.

The agent calls `delete_share` and streams the confirmation back. This confirms to the user that the specific tunnel has been successfully terminated and removed from service.

This server manages account details, including usage limits and authentication credentials. Your agent reads this information via the `get_account` tool to inform the user about their remaining capacity.

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