How to Use the Duffel Flights MCP in Vercel AI SDK

Q: How do I set up Duffel Flights with the Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with your Vinkius MCP endpoint. Pass the tools directly into your text generator and close the connection when the session ends.

Q: Can I stream flight seat maps using Duffel Flights and Vercel AI SDK?

Yes. Use listaircraft to get the equipment details, then let your agent render the layout in real-time using React server components.

Q: Does Duffel Flights support multi-passenger bookings in Vercel AI SDK?

Absolutely. Pass the passenger array to createflightofferrequest as a JSON string, and the SDK will stream the structured offer list back to your UI.

Q: How do I handle flight order listings?

Call listflightorders to fetch the user's booking history. Your agent can parse the response and display a clean list of past trips.

Stream flight search and booking results directly into your Next.js UI using Duffel Flights and Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duffel Flights MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time flight streaming with Vercel AI SDK

Your users don't want to stare at a blank loading screen while searching for flights. By hooking up this MCP Server to your TypeScript frontend, you can feed live options directly into your UI components using `create_flight_offer_request` as the user types. The tool instantly fetches live inventory, letting your agent run `list_flight_offers` to populate React cards on the fly. No waiting for a massive API payload to resolve before showing the first route.

Direct booking and payment from the edge

Run your booking flows on Edge Functions without hitting timeout limits. When a user selects a seat, your agent triggers `create_flight_order` to claim the ticket immediately, keeping latency under a few milliseconds. Once the hold is confirmed, the Vercel AI SDK coordinates with the MCP Server to call `pay_for_flight_order` to process the transaction. You get clean, typed flight orders streaming straight back to the client session.

Instant airport and airline auto-complete

Stop writing heavy database lookups for static flight metadata. This MCP Server exposes `list_airports` and `list_airlines` tools that your agent calls to resolve messy user inputs into exact IATA codes. The agent matches "NYC" to JFK or LGA instantly, then references `list_aircraft` to show the exact plane model in the UI. It keeps your bundle size tiny because the LLM handles the heavy parsing.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` with your Vinkius MCP endpoint. Pass the tools directly into your text generator and close the connection when the session ends.

Yes. Use `list_aircraft` to get the equipment details, then let your agent render the layout in real-time using React server components.

Absolutely. Pass the passenger array to `create_flight_offer_request` as a JSON string, and the SDK will stream the structured offer list back to your UI.

Call `list_flight_orders` to fetch the user's booking history. Your agent can parse the response and display a clean list of past trips.

Yes. Your Duffel API keys and passenger details are isolated in a secure V8 sandbox on Vinkius. We never store credit card details or booking records locally; they go straight to Duffel's secure API.

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