How to Use the Infinity MCP in Vercel AI SDK

Q: How does Infinity handle streaming data with the Vercel ai-sdk?

The server uses listboarditems to fetch tasks and streams the raw JSON chunks through the Vercel ai-sdk. Your frontend maps these chunks directly to UI components, showing tasks as they load.

Q: How do I manage custom fields in Infinity using the Vercel ai-sdk?

You call listboardattributes to get the field definitions. The ai-sdk then passes these IDs to createboarditem, ensuring your custom columns and dropdowns update correctly.

Q: How do I connect the MCP Server to my Vercel ai-sdk project?

You initialize the client using createMCPClient with your secure Vinkius HTTP URL. Then, pass the tools returned by mcpClient.tools() directly into your streamText function call.

Render live task updates and board items directly in your React frontend with the 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 Infinity MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Infinity board data directly to your frontend

Forget loading spinners. When your user asks to see their workspace, this MCP Server grabs the active tasks using `list_board_items` and streams them straight into your React components. The Vercel AI SDK handles the UI updates on the fly so the user sees their boards populate in real-time. You can also fetch the entire structure using `list_board_folders` to build dynamic sidebars. Because this runs on Edge Functions, your app stays fast while pulling live data directly from the Infinity API.

Edit and create tasks in real-time with the MCP Server

Let users create new cards on the fly. Your React frontend captures the user's prompt, and the Vercel AI SDK invokes `create_board_item` to push the new card to the board. The UI updates instantly as the server returns the new item. If they need to change a status, the agent triggers `update_board_item` behind the scenes. Your users get a fast, desktop-grade interface that syncs with their workspace without manual page reloads.

Map board fields dynamically inside your Next.js app

Infinity boards are highly customizable, which usually makes frontend forms a pain to build. This client solves that by calling `list_board_attributes` to inspect the exact schema of your board before rendering the UI. Your Next.js app receives these custom fields over the stream, allowing your agent to correctly format inputs for `create_board_item` on the first try. No hardcoded forms, no broken schemas.

Setup guide

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

The server uses `list_board_items` to fetch tasks and streams the raw JSON chunks through the Vercel ai-sdk. Your frontend maps these chunks directly to UI components, showing tasks as they load.

Yes. The client setup is fully compatible with Edge Functions. You can initialize the server endpoint and stream board updates like `list_board_folders` with minimal latency.

You call `list_board_attributes` to get the field definitions. The ai-sdk then passes these IDs to `create_board_item`, ensuring your custom columns and dropdowns update correctly.

You initialize the client using `createMCPClient` with your secure Vinkius HTTP URL. Then, pass the tools returned by `mcpClient.tools()` directly into your `streamText` function call.

Your API tokens and board data never touch third-party servers. All requests to fetch comments with `list_item_comments` or edit items are run inside isolated V8 sandboxes on Vinkius, keeping your workspace credentials safe.

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