How to Use the Duda MCP in Vercel AI SDK

Q: How do I search for a Duda site using the Vercel AI SDK?

You call the searchsitesbydomain tool within your generateText or streamText function. Pass the domain keyword as an argument and the SDK will handle the tool execution flow. It returns the matching site data to your frontend immediately.

Q: Can the Vercel AI SDK handle Duda site audits?

Yes, you map the quicksitehealthaudit tool to your agent's tool set. The agent then runs the audit and returns the summary for you to display. It works exactly like any other function call in your component.

Q: How do I list site templates with Duda and Vercel AI SDK?

You provide listsitetemplates to your agent's tool definition. When the user asks for available designs, the agent triggers the call and presents the list to your frontend. It is a standard tool integration.

Stream Duda site health and client data directly into your Vercel AI SDK frontends for live, interactive dashboards.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duda MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time site status in your Vercel AI SDK

Feed live site data directly into your frontend components as the AI processes it. You can trigger `quick_site_health_audit` and watch the results populate your React or Next.js UI without waiting for a backend cycle. Your users see exactly what the agent finds the moment it checks `list_published_websites`. It removes the lag between an AI decision and the data showing up on screen.

Manage Duda site inventory via Edge Functions

Run site discovery directly from your serverless functions. Use `list_duda_sites` to grab your entire portfolio and filter results in memory before rendering them. It handles the heavy lifting of API requests while you focus on the UI. The Vercel AI SDK handles the tool calls, keeping your code clean and your site lists current.

Instant client account lookups

Connect your user profiles to actual Duda account data. `get_client_account_profile` pulls specific permission sets that you can use to conditionally render UI elements. Your app stays in sync with your organization's hierarchy. This MCP Server ensures the agent always has the latest account status when a user asks for a profile update.

Setup guide

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

You call the `search_sites_by_domain` tool within your generateText or streamText function. Pass the domain keyword as an argument and the SDK will handle the tool execution flow. It returns the matching site data to your frontend immediately.

Yes, you map the `quick_site_health_audit` tool to your agent's tool set. The agent then runs the audit and returns the summary for you to display. It works exactly like any other function call in your component.

Your credentials never touch the browser. The Vercel AI SDK communicates with the server via the protocol, and the Duda API handles the authentication tokens on the server side. Data is encrypted in transit and never stored on the client.

The MCP Server supports streaming results back to your AI client. You can use the Vercel AI SDK streamText method to watch the list populate as the API responds. It keeps your UI responsive during large data fetches.

You provide `list_site_templates` to your agent's tool definition. When the user asks for available designs, the agent triggers the call and presents the list to your frontend. It is a standard tool integration.

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