How to Use the Ada MCP in Vercel AI SDK

Q: How do I authenticate my Vercel AI SDK app with Ada?

Use the authProvider option inside your Vercel AI SDK setup. This passes your secure credentials directly to the Ada MCP Server without exposing tokens to the client-side code.

Q: Can I stream Ada chat histories using Vercel AI SDK?

Yes, you can. By passing the listconversations tool to your streamText function, the SDK pulls support logs and streams them word-by-word into your React components.

Q: Do I need to manually close the Vercel AI SDK connection after fetching Ada articles?

Yes, always call mcpClient.close() when your query completes. This prevents memory leaks in your Edge Functions when listing articles or updating user profiles.

Feed live Ada customer support threads and help articles directly into your Vercel AI SDK stream without UI lag.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ada MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live chat logs to your Vercel AI SDK UI

Your users hate loading spinners. When you fetch active chats using `list_conversations`, this MCP Server feeds those support transcripts straight into your Next.js frontend as they happen. The Vercel AI SDK handles the UI rendering while the Ada server pulls the raw logs. That means your custom dashboard displays user issues instantly without blocking the main thread.

Real-time knowledge updates with Vercel AI SDK

You can write new help files using `create_article` while the user watches the progress bar fill up. If a support rep updates a policy, the SDK pushes it to the Ada knowledge base and updates the UI instantly. Your frontend stays in sync because the server lets you check existing content via `list_articles` on the edge. No slow database queries, just clean TypeScript code running close to your users.

Instant customer lookups on the Edge

Pulling profile data from Ada shouldn't slow down your app. By calling `get_end_user` through this MCP Server, you fetch metadata and user profiles directly inside your Edge Functions. The SDK handles the streaming response so your support dashboard populates user details piece by piece. Your agents get the context they need before the customer even finishes typing their issue.

Setup guide

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

Use the `authProvider` option inside your Vercel AI SDK setup. This passes your secure credentials directly to the Ada MCP Server without exposing tokens to the client-side code.

Yes, you can. By passing the `list_conversations` tool to your `streamText` function, the SDK pulls support logs and streams them word-by-word into your React components.

It runs on Vinkius's isolated infrastructure, which handles the load easily. Your Vercel AI SDK client calls the server over secure HTTP, keeping your serverless functions light and fast.

Yes, always call `mcpClient.close()` when your query completes. This prevents memory leaks in your Edge Functions when listing articles or updating user profiles.

Vinkius runs the server in an ephemeral sandbox. Your customer chat histories, support profiles, and internal help articles are processed in memory and never stored on Vinkius disks.

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