How to Use the BotPenguin MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream BotPenguin chat history?

Yes. By calling getchathistory, your agent retrieves the full log of a conversation. The SDK then streams this text block directly to your React or Next.js frontend.

Q: Does BotPenguin support user verification via Vercel AI SDK?

It does. Your agent triggers sendotp to dispatch a verification text message. The user enters the code, and your app verifies it instantly.

Feed BotPenguin chat logs and contact updates directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BotPenguin MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live chat feeds in your Vercel AI SDK UI

Your AI client uses `list_chats` to fetch active conversations and immediately display them to users. The tool pulls live sessions from your dashboard, letting the agent analyze who is waiting for a response. Because this MCP server runs on V8 isolates, you get sub-millisecond start times on Vercel Edge Functions. The SDK streams the text chunks instantly, so users see the chat history build up on their screen instead of staring at a blank loader.

Send messages and OTP codes instantly

Sending messages directly to active chats happens through `send_message`, which routes text from your agent to the user's screen. When a user needs identity verification, the `send_otp` tool fires a one-time SMS verification code to their phone. Integrating this MCP server requires calling `mcpClient.tools()` and passing the array directly into your stream. The agent decides when to trigger the SMS or reply to a thread based on the user's prompt.

Access customer tags and profiles

The `get_contact` tool pulls detailed customer profiles, including their assigned labels and contact info. Your agent checks these details to understand who they are talking to before writing a reply. By combining this with `list_tags`, the agent filters users based on their support tier. You manage access tokens through the authProvider config, keeping credentials out of your client-side bundle.

Setup guide

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

Run npm install ai @ai-sdk/mcp to get started. You initialize the connection using createMCPClient with your Vinkius HTTP endpoint.

Yes. By calling `get_chat_history`, your agent retrieves the full log of a conversation. The SDK then streams this text block directly to your React or Next.js frontend.

It does. Your agent triggers `send_otp` to dispatch a verification text message. The user enters the code, and your app verifies it instantly.

Call mcpClient.close() at the end of your execution block. This prevents socket leaks and keeps your serverless functions running efficiently.

Vinkius runs each MCP server connection inside an isolated, zero-trust V8 sandbox. Your customer contact details and chat histories never persist on our servers, as all data transfers through ephemeral, encrypted tunnels.

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