How to Use the Authkey MCP in Vercel AI SDK

Q: How do I connect Authkey to Vercel AI SDK?

Pass your Vinkius URL into createMCPClient({ transport: { type: "http", url: "..." } }). Extract the tools with mcpClient.tools() and feed them into generateText or streamText.

Q: Can Vercel AI SDK stream Authkey MCP delivery statuses?

Yes. When the agent checks getsmsstatus or getemailstatus, the Vercel AI SDK streams the delivery confirmation into your frontend components instantly.

Q: What happens if an Authkey MCP Server request fails?

The checkauthkeystatus tool verifies connectivity before attempting a send. If the HTTP transport drops, your Next.js error boundary catches the failure.

Q: How do I check account balances through the UI?

Your agent calls checkbalance and formats the remaining credits as a React component. The user asks for their balance, and the current number appears on screen.

Build real-time messaging interfaces by connecting the Authkey MCP Server directly to your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authkey MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Authkey MCP Server OTPs into React

The `send_otp` and `verify_otp` tools let your Vercel AI SDK agent manage two-factor authentication directly from a chat interface. Users request a code, and the frontend streams the confirmation immediately. You pass the Vinkius endpoint URL to `createMCPClient`. When the user submits the code, the agent calls the verify endpoint and updates the UI state without waiting for a full page reload.

Build live SMS dashboards

The `list_sms_history` and `get_sms_status` endpoints feed delivery metrics straight to your Svelte or Vue components. Customers ask about their message, and the agent pulls the exact delivery timestamp. Getting this working requires calling `mcpClient.tools()` and passing the array to `streamText`. The AI determines which status to check, executes the call, and renders the result as a text stream.

Trigger voice calls from chat

The `send_voice` tool initiates automated phone calls while the user watches the status update in the browser. They type a prompt, and the system dials the number. You can also monitor the call progress using `get_voice_status`. Always remember to call `mcpClient.close()` when the session ends to prevent hanging connections.

Setup guide

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

Pass your Vinkius URL into `createMCPClient({ transport: { type: "http", url: "..." } })`. Extract the tools with `mcpClient.tools()` and feed them into `generateText` or `streamText`.

Yes. When the agent checks `get_sms_status` or `get_email_status`, the Vercel AI SDK streams the delivery confirmation into your frontend components instantly.

The `check_authkey_status` tool verifies connectivity before attempting a send. If the HTTP transport drops, your Next.js error boundary catches the failure.

Your agent calls `check_balance` and formats the remaining credits as a React component. The user asks for their balance, and the current number appears on screen.

The Vinkius V8 Isolate Sandbox destroys itself after the request. Your phone numbers, email addresses, and OTP codes pass through ephemeral memory and never touch persistent storage.

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