How to Use the Duffel MCP in Vercel AI SDK

Q: How do I connect the Duffel MCP server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into streamText and close the connection when the request finishes.

Q: Can I handle multi-passenger bookings using Duffel with Vercel AI SDK?

Yes. You pass the complete passenger array into the createofferrequest tool, which returns matching offers for the whole group.

Q: How does the Vercel AI SDK handle expired flight offers from Duffel?

If an offer expires, the agent uses priceoffer to detect the failure. You can then write a prompt instruction that tells the agent to run a new search automatically.

Q: Can users select hotel rooms through this setup?

Yes, you use searchstays and fetchstayrates to show accommodation options. The user can view rates and confirm the booking live in the chat.

Let your users search and book flights or stays live inside 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 Duffel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live search streaming for travel offers

`create_offer_request` initiates the search process by sending traveler details and routing options directly to airline APIs. You can pipe these raw flight offers straight to your Vercel AI SDK interface as the backend processes them. Instead of showing a blank screen while waiting for slow GDS systems, the MCP server lets your frontend stream options incrementally. Your users watch flight cards populate one by one via `list_offers` as soon as the carrier responds.

Price checks with Vercel AI SDK

`price_offer` verifies the final cost, baggage policies, and available seat configurations before your user commits to a purchase. This tool prevents stale pricing errors right at the checkout step. Integrating this check into your Next.js edge functions ensures minimal latency. The agent can immediately flag price jumps or cabin changes to the user before running the final booking call.

Interactive seat maps and order creation

`get_seat_maps` pulls the physical layout of the aircraft so your interface can render actual seat selection grids dynamically. Once the user clicks their spot, `create_order` locks in the reservation instantly. The Vercel AI SDK handles this transition by updating the UI state directly from the tool output. You don't have to build complex state machines to bridge the gap between AI generation and actual booking actions.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into `streamText` and close the connection when the request finishes.

Yes. You pass the complete passenger array into the `create_offer_request` tool, which returns matching offers for the whole group.

If an offer expires, the agent uses `price_offer` to detect the failure. You can then write a prompt instruction that tells the agent to run a new search automatically.

Yes, you use `search_stays` and `fetch_stay_rates` to show accommodation options. The user can view rates and confirm the booking live in the chat.

Vinkius runs the server in a zero-trust sandbox, meaning passenger names and passport details are transmitted directly to the API without being cached. Your API tokens are kept in encrypted environment variables that never touch client-side code.

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