How to Use the Aidbase MCP in Vercel AI SDK

Q: How do I start using the Aidbase MCP Server with the Vercel AI SDK?

First, install the packages: npm install ai @ai-sdk/mcp. Then, use createMCPClient with your Vinkius server URL. You can pass the tools from mcpClient.tools() directly to the generateText or streamText functions.

Stream Aidbase support data directly into your React and Svelte apps with the Vercel AI SDK. No more 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 Aidbase MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Knowledge Bases from Your UI

This MCP Server gives you tools to manage your Aidbase knowledge bases directly. You can add new FAQ entries or entire websites as knowledge sources with `add_aidbase_faq_item` and `add_aidbase_website_knowledge`. Because you're using the Vercel AI SDK, the results of these actions can stream directly into your custom admin panel. When you add a new knowledge source, you don't need to wait for a page reload to see it. The new item just appears in your UI in real-time.

Build Live Support Dashboards

Get a complete picture of your Aidbase setup without leaving your application. Use `list_aidbase_chatbots` and `list_aidbase_inboxes` to populate a live dashboard of all your support assets. You can then drill down into specific bots or inboxes with `get_aidbase_chatbot` or `get_aidbase_inbox`. This is perfect for building internal tools for your support team. The AI SDK's streaming capabilities mean your dashboard is always up-to-date, showing new chatbots or knowledge items the moment they're available, without anyone hitting refresh.

Create Custom Chat Interfaces

The `send_aidbase_reply` tool lets you interact directly with any of your chatbots. You can build your own chat widget or testing tool and have your AI client send messages on your behalf. When you pair this with `streamText` from the Vercel AI SDK, the chatbot's response appears word-by-word in your interface. This creates a much more natural user experience than showing a loading animation and then displaying the full text block all at once.

Setup guide

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

First, install the packages: `npm install ai @ai-sdk/mcp`. Then, use `createMCPClient` with your Vinkius server URL. You can pass the tools from `mcpClient.tools()` directly to the `generateText` or `streamText` functions.

Yes. The tools let you list and get details for chatbots, inboxes, and knowledge bases. The Vercel AI SDK is designed to stream this data directly into your React, Svelte, or Vue components for a live-updating UI.

The main benefit is building user-facing features where data appears in real-time. Instead of your user waiting for an API call to finish, they see lists populating and text generating as the AI client works. It's a better experience.

Yes, Vinkius handles the authentication. Your app uses a single endpoint token to connect to the MCP Server. The Vercel AI SDK also supports an `authProvider` for more complex OAuth scenarios if you need it.

This server only touches the Aidbase data needed for a specific tool, like chatbot configurations or knowledge base content. Each request runs in a zero-trust, ephemeral Vinkius sandbox that's destroyed immediately after, so your data isn't stored.

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