How to Use the ngrok MCP in Vercel AI SDK

Q: How do I connect the ngrok MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and set up an HTTP transport. Call createMCPClient with the Vinkius endpoint url, then pass the resulting tools to your streamText function. Always remember to call mcpClient.close() when the stream finishes.

Q: Does the ngrok MCP Server support OAuth via Vercel AI SDK?

It does. You pass an authProvider block into the transport configuration. This handles the Vinkius authentication before the agent ever tries to list your HTTPS edges.

Q: How does this setup handle my private ngrok vault data?

The server only executes read operations like listvaults and listapikeys. Vinkius runs the connector in an ephemeral V8 Isolate Sandbox that destroys itself after the request. Your Vercel AI SDK backend receives the raw JSON, but the MCP layer retains zero state or memory of your internal certificates.

Stream live ngrok tunnel data straight into your React frontend using 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 ngrok MCP to Vercel AI SDK

Create your Vinkius account to connect ngrok 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 ngrok with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream ngrok endpoints with Vercel AI SDK

Building a developer portal means showing active tunnels without making users wait for a spinner. You connect this MCP Server to your Vercel AI SDK backend and stream the results of `list_endpoints` straight to the DOM. React Server Components handle the data fetch while the user watches the active tunnel list populate in real-time. End-users get immediate feedback. When they need to verify their reserved URLs, the agent calls `list_reserved_domains` and pushes the exact domain strings into the UI as they arrive. You don't build custom polling loops. The SDK manages the streaming state while the MCP standard handles the ngrok API transport.

Audit IP policies live

Security teams hate flying blind when it comes to ingress rules. Your Next.js app can now ask the agent to pull current access controls using `list_ip_policies` and `list_ip_restrictions`. The AI reads the raw JSON and formats it into a readable table component on the fly. This changes how you build internal admin tools. Instead of writing custom API wrappers for ngrok, you pass the tool array from `mcpClient.tools()` into `streamText`. The agent grabs the active rules, spots misconfigurations, and renders the alert directly in your Svelte or Vue interface.

Render credential data instantly

Managing edge configurations requires knowing exactly who holds which credentials. Calling `list_api_keys` through the agent lets you build an interactive audit interface. The AI client pulls the active keys and streams the metadata into your frontend layout. You also get visibility into certificate storage. The agent executes `list_vaults` to check where edge certificates live. Because Vercel AI SDK handles the tool execution asynchronously, your UI stays responsive while the agent fetches the vault details from the ngrok backend.

Setup guide

Set up ngrok 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 ngrok 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 ngrok 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 ngrok. 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 ngrok 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 ngrok MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up an HTTP transport. Call `createMCPClient` with the Vinkius endpoint url, then pass the resulting tools to your `streamText` function. Always remember to call `mcpClient.close()` when the stream finishes.

Yes. The SDK natively supports streaming tool calls. When the agent triggers `list_endpoints`, the resulting tunnel data streams directly into your React Server Components as it resolves.

It does. You pass an `authProvider` block into the transport configuration. This handles the Vinkius authentication before the agent ever tries to list your HTTPS edges.

The tool call returns an error object to the AI. Your frontend code needs to catch that rejection within the `generateText` response and render a fallback UI.

The server only executes read operations like `list_vaults` and `list_api_keys`. Vinkius runs the connector in an ephemeral V8 Isolate Sandbox that destroys itself after the request. Your Vercel AI SDK backend receives the raw JSON, but the MCP layer retains zero state or memory of your internal certificates.

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