How to Use the Mav MCP in Vercel AI SDK

Q: How do I configure Mav with Vercel AI SDK using an MCP Server?

Install @ai-sdk/mcp and import the client creator. Pass the Vinkius endpoint URL directly into createMCPClient to start triggering SMS playbooks.

Q: Can I stream Mav playbook status live using Vercel AI SDK?

Yes, you can. Use streamText from the SDK to pipe live updates of your SMS lead qualification from the MCP Server straight to your React or Next.js frontend.

Q: How does Mav handle API keys in Vercel AI SDK?

Use the built-in authProvider option when setting up your client. This secures your SMS gateway credentials without hardcoding secrets in your frontend repository.

Q: Do I need to manually close the connection?

Yes. Always invoke mcpClient.close() when your execution block finishes to avoid hanging connections in your serverless environment.

Get Mav SMS lead qualification updates live on your 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 Mav MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live SMS Playbook Monitoring via Vercel AI SDK

The Mav MCP Server connects your frontend directly to your SMS qualification pipeline. Using the Vercel AI SDK, you can pipe real-time conversation updates straight to your dashboard without annoying page refreshes. Your users watch Mav trigger playbooks and qualify leads as it happens. Setting this up takes minutes. You initialize the connection with `createMCPClient` and pass the tools directly into `streamText`. This keeps your edge functions fast and your database free from constant polling.

Instant Edge-Compatible Lead Qualification

Edge functions demand lightweight, fast connections. This MCP Server runs inside a secure V8 sandbox, allowing your Vercel AI SDK setup to trigger Mav playbooks instantly without cold-start penalties. You get immediate execution when a new lead drops in. By calling `mcpClient.tools()`, your serverless environment gains direct access to the SMS engine. We handle the connectivity so you don't have to build custom API wrappers or manage complex state machines on your own.

Secure Token Management for SMS Workflows

Security shouldn't slow down your development. The MCP integration supports `authProvider` out of the box, letting you manage user tokens without exposing raw credentials to the client side. Your AI client handles the handshake while you focus on building the interface. Once the qualification sequence finishes, simply call `mcpClient.close()` to tear down the connection. It keeps your active sessions clean and prevents memory leaks in serverless environments.

Setup guide

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

Install `@ai-sdk/mcp` and import the client creator. Pass the Vinkius endpoint URL directly into `createMCPClient` to start triggering SMS playbooks.

Yes, you can. Use `streamText` from the SDK to pipe live updates of your SMS lead qualification from the MCP Server straight to your React or Next.js frontend.

Use the built-in `authProvider` option when setting up your client. This secures your SMS gateway credentials without hardcoding secrets in your frontend repository.

Yes. Always invoke `mcpClient.close()` when your execution block finishes to avoid hanging connections in your serverless environment.

Your phone numbers and opt-in records go straight to Mav's secure gateway. Vinkius runs the connector in an isolated, ephemeral sandbox that never stores or logs your customer conversation histories.

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