How to Use the FareHarbor MCP in Vercel AI SDK

Q: How do I handle FareHarbor rate limits inside Vercel AI SDK?

You should cache the results of listavailabilitiesbyrange at the edge to avoid hitting API caps during peak traffic. If a rate limit occurs, the MCP client handles the error state gracefully in your UI components.

Q: Can I stream live FareHarbor tour options to Vercel AI SDK?

Yes, you can stream live options. The agent calls listitems and feeds the JSON array directly into the stream, allowing your UI to render tour cards progressively.

Q: What is the fastest way to verify a booking's status?

Call getbooking with the specific UUID. This returns the complete reservation record, including payment status and customer details, in a single round-trip.

Q: How does Vercel AI SDK protect sensitive customer booking details?

Customer names, emails, and phone numbers processed during createbooking run in an isolated V8 sandbox. This setup ensures sensitive booking payloads never persist on external logging platforms.

Let your users book tours in real-time by streaming live FareHarbor availability directly into your React components with 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 FareHarbor MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time inventory feeds in Vercel AI SDK

Using `list_availabilities_by_range` inside your stream lets you bypass full page reloads when users search for local tours. This setup feeds raw schedule data directly into your active UI components, removing the need for loading spinners. This setup means your MCP agent displays open slots as they stream from the FareHarbor API. The user selects a time from the dynamic list and books instantly via `create_booking` before the slot disappears.

Dynamic lodging lookups during checkout

Fetching pickup spots with `list_lodgings` keeps your checkout flow moving without page stalls. This MCP Server lets your Next.js app fetch current pickup spots as the user types their hotel name. Your Vercel AI SDK agent processes the text input, matches it to the operator's authorized lodging list, and updates the checkout state. No extra API endpoints to write on your backend.

Instant affiliate verification on the edge

Calling `get_me` verifies your affiliate credentials directly on the edge before rendering any booking views. The server confirms your identity across multiple tour companies without introducing cold starts. Using this MCP setup inside edge-compatible routes ensures your application loads correct rates from `list_items` instantly. It keeps your interface fast and prevents booking failures caused by invalid affiliate IDs.

Setup guide

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

You should cache the results of `list_availabilities_by_range` at the edge to avoid hitting API caps during peak traffic. If a rate limit occurs, the MCP client handles the error state gracefully in your UI components.

Yes, you can stream live options. The agent calls `list_items` and feeds the JSON array directly into the stream, allowing your UI to render tour cards progressively.

The server tracks sessions using Vercel AI SDK's built-in state management. When a user books via `create_booking`, the resulting UUID is saved to the chat history to allow subsequent updates with `get_booking`.

Call `get_booking` with the specific UUID. This returns the complete reservation record, including payment status and customer details, in a single round-trip.

Customer names, emails, and phone numbers processed during `create_booking` run in an isolated V8 sandbox. This setup ensures sensitive booking payloads never persist on external logging platforms.

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