How to Use the Cronofy MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream Cronofy event data to Next.js?

Yes. When the model invokes readevents, the SDK pushes the raw JSON payload down to the client immediately. You map that data to your React components to show events as they arrive.

Q: How do I check availability across multiple users?

Call queryavailability with an array of user IDs. The server checks the underlying providers and returns the exact overlapping free blocks.

Connect Cronofy to your Vercel AI SDK apps and stream live calendar availability directly into your React frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cronofy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Vercel AI SDK Scheduling UIs

You pass `read_events` and `query_availability` into your Vercel AI SDK MCP tool registry to let the model check schedules across Google, iCloud, and Exchange simultaneously. The real magic happens when you stream the results straight to the user's browser without waiting for the entire LLM response to finish generating. Your Next.js app renders the available time slots the millisecond the Cronofy MCP Server returns the payload. Users click a button to book, triggering `create_event` in the background while the UI updates instantly via Edge Functions.

Unify Multi-Provider Calendars

Exposing `list_calendars` to your agent gives it immediate read access to every connected schedule regardless of the underlying provider. It pulls unified data structures instead of juggling separate API clients for Microsoft and Apple ecosystems. When a user asks about their schedule tomorrow, the model calls `get_free_busy` to calculate exact overlaps. It processes the raw JSON and streams back a human-readable summary alongside a rendered calendar component.

Handle Complex Booking Logic

Firing off a `create_scheduling_request` lets the AI generate native booking links for external participants. You avoid building custom date-picker forms from scratch while still keeping the user inside your application. If someone cancels, the agent runs `delete_event` to wipe the record out of the provider's database. The Vinkius MCP setup handles the underlying authentication, so your frontend code stays clean and focused on rendering the UI.

Setup guide

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

Install @ai-sdk/mcp and initialize the HTTP transport pointing to your Vinkius endpoint. Pass the resulting tool array into streamText to let the model interact with the calendar data.

Yes. When the model invokes read_events, the SDK pushes the raw JSON payload down to the client immediately. You map that data to your React components to show events as they arrive.

The MCP Server runs remotely on Vinkius, meaning your Edge Functions only need to make standard HTTP calls. You never load heavy calendar SDKs into your edge bundles.

Call query_availability with an array of user IDs. The server checks the underlying providers and returns the exact overlapping free blocks.

Vinkius runs this integration inside an ephemeral V8 Isolate Sandbox. Every time the model queries meeting titles or participant lists, the container spins up, executes the request, and instantly destroys itself, leaving zero residual data behind.

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